From 3aad66cf00d3b551cafb3376a34c50cff62688d4 Mon Sep 17 00:00:00 2001 From: yuukos Date: Thu, 12 Oct 2017 22:24:20 +0700 Subject: [PATCH 1/8] added russian language support --- spacy/ru/__init__.py | 56 ++++++++++++++++++++++++++++++++ spacy/ru/language_data.py | 18 ++++++++++ spacy/ru/stop_words.py | 54 ++++++++++++++++++++++++++++++ spacy/ru/tokenizer_exceptions.py | 29 +++++++++++++++++ 4 files changed, 157 insertions(+) create mode 100644 spacy/ru/__init__.py create mode 100644 spacy/ru/language_data.py create mode 100644 spacy/ru/stop_words.py create mode 100644 spacy/ru/tokenizer_exceptions.py diff --git a/spacy/ru/__init__.py b/spacy/ru/__init__.py new file mode 100644 index 000000000..d8f38e199 --- /dev/null +++ b/spacy/ru/__init__.py @@ -0,0 +1,56 @@ +# encoding: utf8 +from __future__ import unicode_literals, print_function + +from ..language import Language +from ..attrs import LANG +from ..tokens import Doc +from .language_data import * + + +class RussianTokenizer(object): + try: + from pymorphy2 import MorphAnalyzer + except ImportError: + raise ImportError( + "The Russian tokenizer requires the pymorphy2 library: " + "try to fix it with " + "pip install pymorphy2==0.8") + + _morph = MorphAnalyzer() + + def __init__(self, spacy_tokenizer, cls, nlp=None): + self.vocab = nlp.vocab if nlp else cls.create_vocab(nlp) + self._spacy_tokenizer = spacy_tokenizer + + def __call__(self, text): + words = [self._normalize(RussianTokenizer._get_word(token)) + for token in self._spacy_tokenizer(text)] + + return Doc(self.vocab, words, [False] * len(words)) + + @staticmethod + def _get_word(token): + return token.lemma_ if len(token.lemma_) > 0 else token.text + + @classmethod + def _normalize(cls, word): + return cls._morph.parse(word)[0].normal_form + + +class RussianDefaults(Language.Defaults): + lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters[LANG] = lambda text: 'ru' + + tokenizer_exceptions = TOKENIZER_EXCEPTIONS + stop_words = STOP_WORDS + + @classmethod + def create_tokenizer(cls, nlp=None): + tokenizer = super(RussianDefaults, cls).create_tokenizer(nlp) + return RussianTokenizer(tokenizer, cls, nlp) + + +class Russian(Language): + lang = 'ru' + + Defaults = RussianDefaults diff --git a/spacy/ru/language_data.py b/spacy/ru/language_data.py new file mode 100644 index 000000000..75ca41b65 --- /dev/null +++ b/spacy/ru/language_data.py @@ -0,0 +1,18 @@ +# encoding: utf8 +from __future__ import unicode_literals + +from .. import language_data as base +from ..language_data import update_exc, strings_to_exc + +from .stop_words import STOP_WORDS +from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS + + +STOP_WORDS = set(STOP_WORDS) +TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS) + + +update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS)) + + +__all__ = ["STOP_WORDS", "TOKENIZER_EXCEPTIONS"] \ No newline at end of file diff --git a/spacy/ru/stop_words.py b/spacy/ru/stop_words.py new file mode 100644 index 000000000..ddb28af86 --- /dev/null +++ b/spacy/ru/stop_words.py @@ -0,0 +1,54 @@ +# encoding: utf8 +from __future__ import unicode_literals + + +STOP_WORDS = set(""" +а + +будем будет будете будешь буду будут будучи будь будьте бы был была были было +быть + +в вам вами вас весь во вот все всё всего всей всем всём всеми всему всех всею +всея всю вся вы + +да для до + +его едим едят ее её ей ел ела ем ему емъ если ест есть ешь еще ещё ею + +же + +за + +и из или им ими имъ их + +к как кем ко когда кого ком кому комья которая которого которое которой котором +которому которою которую которые который которым которыми которых кто + +меня мне мной мною мог моги могите могла могли могло могу могут мое моё моего +моей моем моём моему моею можем может можете можешь мои мой моим моими моих +мочь мою моя мы + +на нам нами нас наса наш наша наше нашего нашей нашем нашему нашею наши нашим +нашими наших нашу не него нее неё ней нем нём нему нет нею ним ними них но + +о об один одна одни одним одними одних одно одного одной одном одному одною +одну он она оне они оно от + +по при + +с сам сама сами самим самими самих само самого самом самому саму свое своё +своего своей своем своём своему своею свои свой своим своими своих свою своя +себе себя собой собою + +та так такая такие таким такими таких такого такое такой таком такому такою +такую те тебе тебя тем теми тех то тобой тобою того той только том томах тому +тот тою ту ты + +у уже + +чего чем чём чему что чтобы + +эта эти этим этими этих это этого этой этом этому этот этою эту + +я +""".split()) \ No newline at end of file diff --git a/spacy/ru/tokenizer_exceptions.py b/spacy/ru/tokenizer_exceptions.py new file mode 100644 index 000000000..8df57a402 --- /dev/null +++ b/spacy/ru/tokenizer_exceptions.py @@ -0,0 +1,29 @@ +# encoding: utf8 +from __future__ import unicode_literals + +from ..symbols import * + + +TOKENIZER_EXCEPTIONS = { + "Пн.": [ + {ORTH: "Пн.", LEMMA: "Понедельник"} + ], + "Вт.": [ + {ORTH: "Вт.", LEMMA: "Вторник"} + ], + "Ср.": [ + {ORTH: "Ср.", LEMMA: "Среда"} + ], + "Чт.": [ + {ORTH: "Чт.", LEMMA: "Четверг"} + ], + "Пт.": [ + {ORTH: "Пт.", LEMMA: "Пятница"} + ], + "Сб.": [ + {ORTH: "Сб.", LEMMA: "Суббота"} + ], + "Вс.": [ + {ORTH: "Вс.", LEMMA: "Воскресенье"} + ], +} \ No newline at end of file From 74011522894a9fa76b3bfdee17a7e469e4d0214d Mon Sep 17 00:00:00 2001 From: yuukos Date: Fri, 13 Oct 2017 13:57:29 +0700 Subject: [PATCH 2/8] updated Russian tokenizer moved the trying to import pymorph into __init__ --- spacy/ru/__init__.py | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/spacy/ru/__init__.py b/spacy/ru/__init__.py index d8f38e199..12b480a8a 100644 --- a/spacy/ru/__init__.py +++ b/spacy/ru/__init__.py @@ -8,17 +8,19 @@ from .language_data import * class RussianTokenizer(object): - try: - from pymorphy2 import MorphAnalyzer - except ImportError: - raise ImportError( - "The Russian tokenizer requires the pymorphy2 library: " - "try to fix it with " - "pip install pymorphy2==0.8") - - _morph = MorphAnalyzer() + _morph = None def __init__(self, spacy_tokenizer, cls, nlp=None): + try: + from pymorphy2 import MorphAnalyzer + except ImportError: + raise ImportError( + "The Russian tokenizer requires the pymorphy2 library: " + "try to fix it with " + "pip install pymorphy2==0.8") + + RussianTokenizer._morph = RussianTokenizer._create_morph(MorphAnalyzer) + self.vocab = nlp.vocab if nlp else cls.create_vocab(nlp) self._spacy_tokenizer = spacy_tokenizer @@ -36,6 +38,12 @@ class RussianTokenizer(object): def _normalize(cls, word): return cls._morph.parse(word)[0].normal_form + @classmethod + def _create_morph(cls, morph_analyzer_class): + if not cls._morph: + cls._morph = morph_analyzer_class() + return cls._morph + class RussianDefaults(Language.Defaults): lex_attr_getters = dict(Language.Defaults.lex_attr_getters) From a0739a06d4de101018f32ae3292d8866f4b9a1b4 Mon Sep 17 00:00:00 2001 From: Vadim Mazaev Date: Fri, 17 Nov 2017 17:06:15 +0300 Subject: [PATCH 3/8] Returned russian support from v1.10 branch --- spacy/{ => lang}/ru/__init__.py | 0 spacy/{ => lang}/ru/language_data.py | 0 spacy/{ => lang}/ru/stop_words.py | 0 spacy/{ => lang}/ru/tokenizer_exceptions.py | 0 4 files changed, 0 insertions(+), 0 deletions(-) rename spacy/{ => lang}/ru/__init__.py (100%) rename spacy/{ => lang}/ru/language_data.py (100%) rename spacy/{ => lang}/ru/stop_words.py (100%) rename spacy/{ => lang}/ru/tokenizer_exceptions.py (100%) diff --git a/spacy/ru/__init__.py b/spacy/lang/ru/__init__.py similarity index 100% rename from spacy/ru/__init__.py rename to spacy/lang/ru/__init__.py diff --git a/spacy/ru/language_data.py b/spacy/lang/ru/language_data.py similarity index 100% rename from spacy/ru/language_data.py rename to spacy/lang/ru/language_data.py diff --git a/spacy/ru/stop_words.py b/spacy/lang/ru/stop_words.py similarity index 100% rename from spacy/ru/stop_words.py rename to spacy/lang/ru/stop_words.py diff --git a/spacy/ru/tokenizer_exceptions.py b/spacy/lang/ru/tokenizer_exceptions.py similarity index 100% rename from spacy/ru/tokenizer_exceptions.py rename to spacy/lang/ru/tokenizer_exceptions.py From 52ee1f9bf93e75df649b2f25f3d106f8602483ea Mon Sep 17 00:00:00 2001 From: Vadim Mazaev Date: Tue, 21 Nov 2017 11:44:46 +0300 Subject: [PATCH 4/8] Updated Russian Language, added lemmatizer, norm exceptions and lex attrs --- spacy/lang/ru/__init__.py | 66 +++----- spacy/lang/ru/language_data.py | 18 -- spacy/lang/ru/lemmatizer.py | 232 ++++++++++++++++++++++++++ spacy/lang/ru/lex_attrs.py | 35 ++++ spacy/lang/ru/norm_exceptions.py | 34 ++++ spacy/lang/ru/tokenizer_exceptions.py | 26 +-- 6 files changed, 323 insertions(+), 88 deletions(-) delete mode 100644 spacy/lang/ru/language_data.py create mode 100644 spacy/lang/ru/lemmatizer.py create mode 100644 spacy/lang/ru/lex_attrs.py create mode 100644 spacy/lang/ru/norm_exceptions.py diff --git a/spacy/lang/ru/__init__.py b/spacy/lang/ru/__init__.py index 12b480a8a..29b6c7082 100644 --- a/spacy/lang/ru/__init__.py +++ b/spacy/lang/ru/__init__.py @@ -1,64 +1,36 @@ # encoding: utf8 from __future__ import unicode_literals, print_function -from ..language import Language -from ..attrs import LANG -from ..tokens import Doc -from .language_data import * +from .stop_words import STOP_WORDS +from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS +from .norm_exceptions import NORM_EXCEPTIONS +from .lex_attrs import LEX_ATTRS +from .lemmatizer import RussianLemmatizer - -class RussianTokenizer(object): - _morph = None - - def __init__(self, spacy_tokenizer, cls, nlp=None): - try: - from pymorphy2 import MorphAnalyzer - except ImportError: - raise ImportError( - "The Russian tokenizer requires the pymorphy2 library: " - "try to fix it with " - "pip install pymorphy2==0.8") - - RussianTokenizer._morph = RussianTokenizer._create_morph(MorphAnalyzer) - - self.vocab = nlp.vocab if nlp else cls.create_vocab(nlp) - self._spacy_tokenizer = spacy_tokenizer - - def __call__(self, text): - words = [self._normalize(RussianTokenizer._get_word(token)) - for token in self._spacy_tokenizer(text)] - - return Doc(self.vocab, words, [False] * len(words)) - - @staticmethod - def _get_word(token): - return token.lemma_ if len(token.lemma_) > 0 else token.text - - @classmethod - def _normalize(cls, word): - return cls._morph.parse(word)[0].normal_form - - @classmethod - def _create_morph(cls, morph_analyzer_class): - if not cls._morph: - cls._morph = morph_analyzer_class() - return cls._morph +from ..tokenizer_exceptions import BASE_EXCEPTIONS +from ..norm_exceptions import BASE_NORMS +from ...util import update_exc, add_lookups +from ...language import Language +from ...attrs import LANG, LIKE_NUM, NORM class RussianDefaults(Language.Defaults): lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters.update(LEX_ATTRS) lex_attr_getters[LANG] = lambda text: 'ru' - - tokenizer_exceptions = TOKENIZER_EXCEPTIONS + lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], + BASE_NORMS, NORM_EXCEPTIONS) + tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) stop_words = STOP_WORDS @classmethod - def create_tokenizer(cls, nlp=None): - tokenizer = super(RussianDefaults, cls).create_tokenizer(nlp) - return RussianTokenizer(tokenizer, cls, nlp) + def create_lemmatizer(cls, nlp=None): + return RussianLemmatizer() class Russian(Language): lang = 'ru' - Defaults = RussianDefaults + + +__all__ = ['Russian'] diff --git a/spacy/lang/ru/language_data.py b/spacy/lang/ru/language_data.py deleted file mode 100644 index 75ca41b65..000000000 --- a/spacy/lang/ru/language_data.py +++ /dev/null @@ -1,18 +0,0 @@ -# encoding: utf8 -from __future__ import unicode_literals - -from .. import language_data as base -from ..language_data import update_exc, strings_to_exc - -from .stop_words import STOP_WORDS -from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS - - -STOP_WORDS = set(STOP_WORDS) -TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS) - - -update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS)) - - -__all__ = ["STOP_WORDS", "TOKENIZER_EXCEPTIONS"] \ No newline at end of file diff --git a/spacy/lang/ru/lemmatizer.py b/spacy/lang/ru/lemmatizer.py new file mode 100644 index 000000000..538c4aaef --- /dev/null +++ b/spacy/lang/ru/lemmatizer.py @@ -0,0 +1,232 @@ +# coding: utf8 +from ...symbols import ( + ADJ, DET, NOUN, NUM, PRON, PROPN, VERB +) +from ...lemmatizer import Lemmatizer + + +class RussianLemmatizer(Lemmatizer): + _morph = None + + def __init__(self): + super().__init__() + try: + from pymorphy2 import MorphAnalyzer + except ImportError: + raise ImportError( + 'The Russian lemmatizer requires the pymorphy2 library: ' + 'try to fix it with "pip install pymorphy2"') + + if RussianLemmatizer._morph is None: + RussianLemmatizer._morph = MorphAnalyzer() + + def __call__(self, string, univ_pos, morphology=None): + univ_pos = self.normalize_univ_pos(univ_pos) + if univ_pos not in ('ADJ', 'DET', 'NOUN', 'NUM', 'PRON', 'PROPN', 'VERB'): + # Skip unchangeable pos + return [string.lower()] + + analyses = self._morph.parse(string) + filtered_analyses = [] + for analysis in analyses: + if not analysis.is_known: + # Skip suggested parse variant for unknown word for pymorphy + continue + analysis_pos, _ = oc2ud(str(analysis.tag)) + if analysis_pos == univ_pos \ + or (analysis_pos in ('NOUN', 'PROPN') and univ_pos in ('NOUN', 'PROPN')): + filtered_analyses.append(analysis) + + if not len(filtered_analyses): + return [string.lower()] + if morphology is None: + return list(set([analysis.normal_form for analysis in filtered_analyses])) + + if univ_pos in ('ADJ', 'DET', 'NOUN', 'PROPN'): + features_to_compare = ['Case', 'Number', 'Gender'] + elif univ_pos == 'NUM': + features_to_compare = ['Case', 'Gender'] + elif univ_pos == 'PRON': + features_to_compare = ['Case', 'Number', 'Gender', 'Person'] + else: # VERB + features_to_compare = ['Aspect', 'Gender', 'Mood', 'Number', 'Tense', 'VerbForm', 'Voice'] + + analyses, filtered_analyses = filtered_analyses, [] + for analysis in analyses: + _, analysis_morph = oc2ud(str(analysis.tag)) + for feature in features_to_compare: + if feature in morphology and morphology[feature] != analysis_morph[feature]: + break + else: + filtered_analyses.append(analysis) + + if not len(filtered_analyses): + return [string.lower()] + return list(set([analysis.normal_form for analysis in filtered_analyses])) + + @staticmethod + def normalize_univ_pos(univ_pos): + if isinstance(univ_pos, str): + return univ_pos.upper() + + symbols_to_str = { + ADJ: 'ADJ', + DET: 'DET', + NOUN: 'NOUN', + NUM: 'NUM', + PRON: 'PRON', + PROPN: 'PROPN', + VERB: 'VERB' + } + if univ_pos in symbols_to_str: + return symbols_to_str[univ_pos] + return None + + def is_base_form(self, univ_pos, morphology=None): + # TODO + raise NotImplementedError + + # ('ADJ', 'DET', 'NOUN', 'NUM', 'PRON', 'PROPN', 'VERB'): + def det(self, string, morphology=None): + return self(string, 'det', morphology) + + def num(self, string, morphology=None): + return self(string, 'num', morphology) + + def pron(self, string, morphology=None): + return self(string, 'pron', morphology) + + def lookup(self, string): + analyses = self._morph.parse(string) + if len(analyses) == 1: + return analyses[0].normal_form + return string + + +def oc2ud(oc_tag): + gram_map = { + '_POS': { + 'ADJF': 'ADJ', + 'ADJS': 'ADJ', + 'ADVB': 'ADV', + 'Apro': 'DET', + 'COMP': 'ADJ', # Can also be an ADV - unchangeable + 'CONJ': 'CCONJ', # Can also be a SCONJ - both unchangeable ones + 'GRND': 'VERB', + 'INFN': 'VERB', + 'INTJ': 'INTJ', + 'NOUN': 'NOUN', + 'NPRO': 'PRON', + 'NUMR': 'NUM', + 'NUMB': 'NUM', + 'PNCT': 'PUNCT', + 'PRCL': 'PART', + 'PREP': 'ADP', + 'PRTF': 'VERB', + 'PRTS': 'VERB', + 'VERB': 'VERB', + }, + 'Animacy': { + 'anim': 'Anim', + 'inan': 'Inan', + }, + 'Aspect': { + 'impf': 'Imp', + 'perf': 'Perf', + }, + 'Case': { + 'ablt': 'Ins', + 'accs': 'Acc', + 'datv': 'Dat', + 'gen1': 'Gen', + 'gen2': 'Gen', + 'gent': 'Gen', + 'loc2': 'Loc', + 'loct': 'Loc', + 'nomn': 'Nom', + 'voct': 'Voc', + }, + 'Degree': { + 'COMP': 'Cmp', + 'Supr': 'Sup', + }, + 'Gender': { + 'femn': 'Fem', + 'masc': 'Masc', + 'neut': 'Neut', + }, + 'Mood': { + 'impr': 'Imp', + 'indc': 'Ind', + }, + 'Number': { + 'plur': 'Plur', + 'sing': 'Sing', + }, + 'NumForm': { + 'NUMB': 'Digit', + }, + 'Person': { + '1per': '1', + '2per': '2', + '3per': '3', + 'excl': '2', + 'incl': '1', + }, + 'Tense': { + 'futr': 'Fut', + 'past': 'Past', + 'pres': 'Pres', + }, + 'Variant': { + 'ADJS': 'Brev', + 'PRTS': 'Brev', + }, + 'VerbForm': { + 'GRND': 'Conv', + 'INFN': 'Inf', + 'PRTF': 'Part', + 'PRTS': 'Part', + 'VERB': 'Fin', + }, + 'Voice': { + 'actv': 'Act', + 'pssv': 'Pass', + }, + 'Abbr': { + 'Abbr': 'Yes' + } + } + + pos = 'X' + morphology = dict() + unmatched = set() + + grams = oc_tag.replace(' ', ',').split(',') + for gram in grams: + match = False + for categ, gmap in sorted(gram_map.items()): + if gram in gmap: + match = True + if categ == '_POS': + pos = gmap[gram] + else: + morphology[categ] = gmap[gram] + if not match: + unmatched.add(gram) + + while len(unmatched) > 0: + gram = unmatched.pop() + if gram in ('Name', 'Patr', 'Surn', 'Geox', 'Orgn'): + pos = 'PROPN' + elif gram == 'Auxt': + pos = 'AUX' + elif gram == 'Pltm': + morphology['Number'] = 'Ptan' + + return pos, morphology + + +if __name__ == '__main__': + l = RussianLemmatizer() + print(l.noun('гвоздики', {'Gender': 'Fem'})) diff --git a/spacy/lang/ru/lex_attrs.py b/spacy/lang/ru/lex_attrs.py new file mode 100644 index 000000000..f3a889cad --- /dev/null +++ b/spacy/lang/ru/lex_attrs.py @@ -0,0 +1,35 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...attrs import LIKE_NUM + + +_num_words = [ + 'ноль', 'один', 'два', 'три', 'четыре', 'пять', 'шесть', 'семь', 'восемь', 'девять', + + 'десять', 'одиннадцать', 'двенадцать', 'тринадцать', 'четырнадцать', + 'пятнадцать', 'шестнадцать', 'семнадцать', 'восемнадцать', 'девятнадцать', + + 'двадцать', 'тридцать', 'сорок', 'пятдесят', 'шестдесят', 'семдесят', 'восемдесят', 'девяносто', + + 'сто', 'двести', 'триста', 'четыреста', 'пятсот', 'шестсот', 'семсот', 'восемсот', 'девятсот', + + 'тысяча', 'миллион', 'миллиад', 'триллион', 'квадриллион', 'квинтиллион'] + + +def like_num(text): + text = text.replace(',', '').replace('.', '') + if text.isdigit(): + return True + if text.count('/') == 1: + num, denom = text.split('/') + if num.isdigit() and denom.isdigit(): + return True + if text in _num_words: + return True + return False + + +LEX_ATTRS = { + LIKE_NUM: like_num +} diff --git a/spacy/lang/ru/norm_exceptions.py b/spacy/lang/ru/norm_exceptions.py new file mode 100644 index 000000000..6c3a5007c --- /dev/null +++ b/spacy/lang/ru/norm_exceptions.py @@ -0,0 +1,34 @@ +# coding: utf8 +from __future__ import unicode_literals + + +_exc = { + # Slang + 'прив': 'привет', + + # Weekdays abbreviations + "пн.": "понедельник", + "вт.": "вторник", + "ср.": "среда", + "чт.": "четверг", + "пт.": "пятница", + "сб.": "суббота", + "вс.": "воскресенье", + + # Months abbreviations + "янв.": "январь", + "фев.": "февраль", + "мар.": "март", + "апр.": "апрель", + +} + + +NORM_EXCEPTIONS = {} + +for string, norm in _exc.items(): + NORM_EXCEPTIONS[string] = norm + NORM_EXCEPTIONS[string.title()] = norm + if string.endswith('.'): + NORM_EXCEPTIONS[string[:-1]] = norm + NORM_EXCEPTIONS[string.title()[:-1]] = norm diff --git a/spacy/lang/ru/tokenizer_exceptions.py b/spacy/lang/ru/tokenizer_exceptions.py index 8df57a402..707dd388c 100644 --- a/spacy/lang/ru/tokenizer_exceptions.py +++ b/spacy/lang/ru/tokenizer_exceptions.py @@ -1,29 +1,9 @@ # encoding: utf8 from __future__ import unicode_literals -from ..symbols import * +from ...symbols import ORTH, LEMMA TOKENIZER_EXCEPTIONS = { - "Пн.": [ - {ORTH: "Пн.", LEMMA: "Понедельник"} - ], - "Вт.": [ - {ORTH: "Вт.", LEMMA: "Вторник"} - ], - "Ср.": [ - {ORTH: "Ср.", LEMMA: "Среда"} - ], - "Чт.": [ - {ORTH: "Чт.", LEMMA: "Четверг"} - ], - "Пт.": [ - {ORTH: "Пт.", LEMMA: "Пятница"} - ], - "Сб.": [ - {ORTH: "Сб.", LEMMA: "Суббота"} - ], - "Вс.": [ - {ORTH: "Вс.", LEMMA: "Воскресенье"} - ], -} \ No newline at end of file + +} From 81314f8659c215e01b6068d134f4ccaa647ba318 Mon Sep 17 00:00:00 2001 From: Vadim Mazaev Date: Tue, 21 Nov 2017 22:23:59 +0300 Subject: [PATCH 5/8] Fixed tokenizer: added char classes; added first lemmatizer and tokenizer tests --- spacy/lang/char_classes.py | 11 ++- spacy/tests/conftest.py | 12 ++- spacy/tests/lang/ru/__init__.py | 0 spacy/tests/lang/ru/test_lemmatizer.py | 71 ++++++++++++++ spacy/tests/lang/ru/test_punct.py | 131 +++++++++++++++++++++++++ 5 files changed, 220 insertions(+), 5 deletions(-) create mode 100644 spacy/tests/lang/ru/__init__.py create mode 100644 spacy/tests/lang/ru/test_lemmatizer.py create mode 100644 spacy/tests/lang/ru/test_punct.py diff --git a/spacy/lang/char_classes.py b/spacy/lang/char_classes.py index 7ec631c92..68d8eecc7 100644 --- a/spacy/lang/char_classes.py +++ b/spacy/lang/char_classes.py @@ -15,9 +15,11 @@ _hebrew = r'[\p{L}&&\p{Hebrew}]' _latin_lower = r'[\p{Ll}&&\p{Latin}]' _latin_upper = r'[\p{Lu}&&\p{Latin}]' _latin = r'[[\p{Ll}||\p{Lu}]&&\p{Latin}]' +_russian_lower = r'[ёа-я]' +_russian_upper = r'[ЁА-Я]' -_upper = [_latin_upper] -_lower = [_latin_lower] +_upper = [_latin_upper, _russian_upper] +_lower = [_latin_lower, _russian_lower] _uncased = [_bengali, _hebrew] ALPHA = merge_char_classes(_upper + _lower + _uncased) @@ -27,8 +29,9 @@ ALPHA_UPPER = merge_char_classes(_upper + _uncased) _units = ('km km² km³ m m² m³ dm dm² dm³ cm cm² cm³ mm mm² mm³ ha µm nm yd in ft ' 'kg g mg µg t lb oz m/s km/h kmh mph hPa Pa mbar mb MB kb KB gb GB tb ' - 'TB T G M K %') -_currency = r'\$ £ € ¥ ฿ US\$ C\$ A\$' + 'TB T G M K % км км² км³ м м² м³ дм дм² дм³ см см² см³ мм мм² мм³ нм ' + 'кг г мг м/с км/ч кПа Па мбар Кб КБ кб Мб МБ мб Гб ГБ гб Тб ТБ тб') +_currency = r'\$ £ € ¥ ฿ US\$ C\$ A\$ ₽' # These expressions contain various unicode variations, including characters # used in Chinese (see #1333, #1340, #1351) – unless there are cross-language diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py index 2d1b03514..73a484c13 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -15,7 +15,7 @@ from .. import util # here if it's using spaCy's tokenizer (not a different library) # TODO: re-implement generic tokenizer tests _languages = ['bn', 'da', 'de', 'en', 'es', 'fi', 'fr', 'ga', 'he', 'hu', 'id', - 'it', 'nb', 'nl', 'pl', 'pt', 'sv', 'xx'] + 'it', 'nb', 'nl', 'pl', 'pt', 'ru', 'sv', 'xx'] _models = {'en': ['en_core_web_sm'], 'de': ['de_core_news_md'], 'fr': ['fr_core_news_sm'], @@ -40,6 +40,11 @@ def FR(request): return load_test_model(request.param) +@pytest.fixture() +def RU(request): + return util.get_lang_class('ru') + + #@pytest.fixture(params=_languages) #def tokenizer(request): #lang = util.get_lang_class(request.param) @@ -137,6 +142,11 @@ def th_tokenizer(): return util.get_lang_class('th').Defaults.create_tokenizer() +@pytest.fixture +def ru_tokenizer(): + return util.get_lang_class('ru').Defaults.create_tokenizer() + + @pytest.fixture def stringstore(): return StringStore() diff --git a/spacy/tests/lang/ru/__init__.py b/spacy/tests/lang/ru/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/spacy/tests/lang/ru/test_lemmatizer.py b/spacy/tests/lang/ru/test_lemmatizer.py new file mode 100644 index 000000000..345bcd971 --- /dev/null +++ b/spacy/tests/lang/ru/test_lemmatizer.py @@ -0,0 +1,71 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import pytest +from ....tokens.doc import Doc + + +@pytest.fixture +def ru_lemmatizer(RU): + return RU.Defaults.create_lemmatizer() + + +# @pytest.mark.models('ru') +# def test_doc_lemmatization(RU): +# doc = Doc(RU.vocab, words=['мама', 'мыла', 'раму']) +# doc[0].tag_ = 'NOUN__Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing' +# doc[1].tag_ = 'VERB__Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act' +# doc[2].tag_ = 'NOUN__Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing' +# +# lemmas = [token.lemma_ for token in doc] +# assert lemmas == ['мама', 'мыть', 'рама'] + + +@pytest.mark.models('ru') +@pytest.mark.parametrize('text,lemmas', [('гвоздики', ['гвоздик', 'гвоздика']), + ('люди', ['человек']), + ('реки', ['река']), + ('кольцо', ['кольцо']), + ('пепперони', ['пепперони'])]) +def test_ru_lemmatizer_noun_lemmas(ru_lemmatizer, text, lemmas): + assert sorted(ru_lemmatizer.noun(text)) == lemmas + + +@pytest.mark.models('ru') +@pytest.mark.parametrize('text,pos,morphology,lemma', [('рой', 'NOUN', None, 'рой'), + ('рой', 'VERB', None, 'рыть'), + ('клей', 'NOUN', None, 'клей'), + ('клей', 'VERB', None, 'клеить'), + ('три', 'NUM', None, 'три'), + ('кос', 'NOUN', {'Number': 'Sing'}, 'кос'), + ('кос', 'NOUN', {'Number': 'Plur'}, 'коса'), + ('кос', 'ADJ', None, 'косой'), + ('потом', 'NOUN', None, 'пот'), + ('потом', 'ADV', None, 'потом') + ]) +def test_ru_lemmatizer_works_with_different_pos_homonyms(ru_lemmatizer, text, pos, morphology, lemma): + assert ru_lemmatizer(text, pos, morphology) == [lemma] + + +@pytest.mark.models('ru') +@pytest.mark.parametrize('text,morphology,lemma', [('гвоздики', {'Gender': 'Fem'}, 'гвоздика'), + ('гвоздики', {'Gender': 'Masc'}, 'гвоздик'), + ('вина', {'Gender': 'Fem'}, 'вина'), + ('вина', {'Gender': 'Neut'}, 'вино') + ]) +def test_ru_lemmatizer_works_with_noun_homonyms(ru_lemmatizer, text, morphology, lemma): + assert ru_lemmatizer.noun(text, morphology) == [lemma] + + +# @pytest.mark.models('ru') +# def test_ru_lemmatizer_punct(ru_lemmatizer): +# assert ru_lemmatizer.punct('“') == ['"'] +# assert ru_lemmatizer.punct('“') == ['"'] +# +# +# @pytest.mark.models('ru') +# def test_ru_lemmatizer_lemma_assignment(RU): +# text = "А роза упала на лапу Азора." +# doc = RU.make_doc(text) +# RU.tagger(doc) +# assert all(t.lemma_ != '' for t in doc) diff --git a/spacy/tests/lang/ru/test_punct.py b/spacy/tests/lang/ru/test_punct.py new file mode 100644 index 000000000..6a689ff71 --- /dev/null +++ b/spacy/tests/lang/ru/test_punct.py @@ -0,0 +1,131 @@ +# coding: utf-8 +"""Test that open, closed and paired punctuation is split off correctly.""" + + +from __future__ import unicode_literals + +import pytest + +from ....util import compile_prefix_regex +from ....lang.punctuation import TOKENIZER_PREFIXES + + +PUNCT_OPEN = ['(', '[', '{', '*'] +PUNCT_CLOSE = [')', ']', '}', '*'] +PUNCT_PAIRED = [('(', ')'), ('[', ']'), ('{', '}'), ('*', '*')] + + +@pytest.mark.parametrize('text', ["(", "((", "<"]) +def test_ru_tokenizer_handles_only_punct(ru_tokenizer, text): + tokens = ru_tokenizer(text) + assert len(tokens) == len(text) + + +@pytest.mark.parametrize('punct', PUNCT_OPEN) +@pytest.mark.parametrize('text', ["Привет"]) +def test_ru_tokenizer_splits_open_punct(ru_tokenizer, punct, text): + tokens = ru_tokenizer(punct + text) + assert len(tokens) == 2 + assert tokens[0].text == punct + assert tokens[1].text == text + + +@pytest.mark.parametrize('punct', PUNCT_CLOSE) +@pytest.mark.parametrize('text', ["Привет"]) +def test_ru_tokenizer_splits_close_punct(ru_tokenizer, punct, text): + tokens = ru_tokenizer(text + punct) + assert len(tokens) == 2 + assert tokens[0].text == text + assert tokens[1].text == punct + + +@pytest.mark.parametrize('punct', PUNCT_OPEN) +@pytest.mark.parametrize('punct_add', ["`"]) +@pytest.mark.parametrize('text', ["Привет"]) +def test_ru_tokenizer_splits_two_diff_open_punct(ru_tokenizer, punct, punct_add, text): + tokens = ru_tokenizer(punct + punct_add + text) + assert len(tokens) == 3 + assert tokens[0].text == punct + assert tokens[1].text == punct_add + assert tokens[2].text == text + + +@pytest.mark.parametrize('punct', PUNCT_CLOSE) +@pytest.mark.parametrize('punct_add', ["'"]) +@pytest.mark.parametrize('text', ["Привет"]) +def test_ru_tokenizer_splits_two_diff_close_punct(ru_tokenizer, punct, punct_add, text): + tokens = ru_tokenizer(text + punct + punct_add) + assert len(tokens) == 3 + assert tokens[0].text == text + assert tokens[1].text == punct + assert tokens[2].text == punct_add + + +@pytest.mark.parametrize('punct', PUNCT_OPEN) +@pytest.mark.parametrize('text', ["Привет"]) +def test_ru_tokenizer_splits_same_open_punct(ru_tokenizer, punct, text): + tokens = ru_tokenizer(punct + punct + punct + text) + assert len(tokens) == 4 + assert tokens[0].text == punct + assert tokens[3].text == text + + +@pytest.mark.parametrize('punct', PUNCT_CLOSE) +@pytest.mark.parametrize('text', ["Привет"]) +def test_ru_tokenizer_splits_same_close_punct(ru_tokenizer, punct, text): + tokens = ru_tokenizer(text + punct + punct + punct) + assert len(tokens) == 4 + assert tokens[0].text == text + assert tokens[1].text == punct + + +@pytest.mark.parametrize('text', ["'Тест"]) +def test_ru_tokenizer_splits_open_appostrophe(ru_tokenizer, text): + tokens = ru_tokenizer(text) + assert len(tokens) == 2 + assert tokens[0].text == "'" + + +@pytest.mark.parametrize('text', ["Тест''"]) +def test_ru_tokenizer_splits_double_end_quote(ru_tokenizer, text): + tokens = ru_tokenizer(text) + assert len(tokens) == 2 + tokens_punct = ru_tokenizer("''") + assert len(tokens_punct) == 1 + + +@pytest.mark.parametrize('punct_open,punct_close', PUNCT_PAIRED) +@pytest.mark.parametrize('text', ["Тест"]) +def test_ru_tokenizer_splits_open_close_punct(ru_tokenizer, punct_open, + punct_close, text): + tokens = ru_tokenizer(punct_open + text + punct_close) + assert len(tokens) == 3 + assert tokens[0].text == punct_open + assert tokens[1].text == text + assert tokens[2].text == punct_close + + +@pytest.mark.parametrize('punct_open,punct_close', PUNCT_PAIRED) +@pytest.mark.parametrize('punct_open2,punct_close2', [("`", "'")]) +@pytest.mark.parametrize('text', ["Тест"]) +def test_ru_tokenizer_two_diff_punct(ru_tokenizer, punct_open, punct_close, + punct_open2, punct_close2, text): + tokens = ru_tokenizer(punct_open2 + punct_open + text + punct_close + punct_close2) + assert len(tokens) == 5 + assert tokens[0].text == punct_open2 + assert tokens[1].text == punct_open + assert tokens[2].text == text + assert tokens[3].text == punct_close + assert tokens[4].text == punct_close2 + + +@pytest.mark.parametrize('text', [("Тест.")]) +def test_ru_tokenizer_splits_trailing_dot(ru_tokenizer, text): + tokens = ru_tokenizer(text) + assert tokens[1].text == "." + + +def test_ru_tokenizer_splits_bracket_period(ru_tokenizer): + text = "(Раз, два, три, проверка)." + tokens = ru_tokenizer(text) + assert tokens[len(tokens) - 1].text == "." From cacd859dcde1da91a64c32e344a9a892eebaf2f3 Mon Sep 17 00:00:00 2001 From: Vadim Mazaev Date: Sun, 26 Nov 2017 20:54:48 +0300 Subject: [PATCH 6/8] Added tag map, fixed tests fails, added more exceptions --- spacy/attrs.pyx | 2 +- spacy/lang/ru/__init__.py | 2 + spacy/lang/ru/lemmatizer.py | 23 +- spacy/lang/ru/norm_exceptions.py | 28 +- spacy/lang/ru/tag_map.py | 731 ++++++++++++++++++ spacy/lang/ru/tokenizer_exceptions.py | 65 +- spacy/tests/conftest.py | 2 +- spacy/tests/lang/ru/test_lemmatizer.py | 30 +- .../ru/{test_punct.py => test_tokenizer.py} | 9 +- spacy/tests/lang/ru/test_tokenizer_exc.py | 16 + 10 files changed, 854 insertions(+), 54 deletions(-) create mode 100644 spacy/lang/ru/tag_map.py rename spacy/tests/lang/ru/{test_punct.py => test_tokenizer.py} (93%) create mode 100644 spacy/tests/lang/ru/test_tokenizer_exc.py diff --git a/spacy/attrs.pyx b/spacy/attrs.pyx index 8113ffebe..893ec0845 100644 --- a/spacy/attrs.pyx +++ b/spacy/attrs.pyx @@ -131,7 +131,7 @@ def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False): 'NumValue', 'PartType', 'Polite', 'StyleVariant', 'PronType', 'AdjType', 'Person', 'Variant', 'AdpType', 'Reflex', 'Negative', 'Mood', 'Aspect', 'Case', - 'Polarity', # U20 + 'Polarity', 'Animacy' # U20 ] for key in morph_keys: if key in stringy_attrs: diff --git a/spacy/lang/ru/__init__.py b/spacy/lang/ru/__init__.py index 29b6c7082..898b48348 100644 --- a/spacy/lang/ru/__init__.py +++ b/spacy/lang/ru/__init__.py @@ -5,6 +5,7 @@ from .stop_words import STOP_WORDS from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .norm_exceptions import NORM_EXCEPTIONS from .lex_attrs import LEX_ATTRS +from .tag_map import TAG_MAP from .lemmatizer import RussianLemmatizer from ..tokenizer_exceptions import BASE_EXCEPTIONS @@ -22,6 +23,7 @@ class RussianDefaults(Language.Defaults): BASE_NORMS, NORM_EXCEPTIONS) tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS) stop_words = STOP_WORDS + tag_map = TAG_MAP @classmethod def create_lemmatizer(cls, nlp=None): diff --git a/spacy/lang/ru/lemmatizer.py b/spacy/lang/ru/lemmatizer.py index 538c4aaef..8ea6255d7 100644 --- a/spacy/lang/ru/lemmatizer.py +++ b/spacy/lang/ru/lemmatizer.py @@ -1,6 +1,6 @@ # coding: utf8 from ...symbols import ( - ADJ, DET, NOUN, NUM, PRON, PROPN, VERB + ADJ, DET, NOUN, NUM, PRON, PROPN, PUNCT, VERB, POS ) from ...lemmatizer import Lemmatizer @@ -9,19 +9,22 @@ class RussianLemmatizer(Lemmatizer): _morph = None def __init__(self): - super().__init__() + super(RussianLemmatizer, self).__init__() try: from pymorphy2 import MorphAnalyzer except ImportError: raise ImportError( 'The Russian lemmatizer requires the pymorphy2 library: ' - 'try to fix it with "pip install pymorphy2"') + 'try to fix it with "pip install pymorphy2==0.8"') if RussianLemmatizer._morph is None: RussianLemmatizer._morph = MorphAnalyzer() def __call__(self, string, univ_pos, morphology=None): univ_pos = self.normalize_univ_pos(univ_pos) + if univ_pos == 'PUNCT': + return [PUNCT_RULES.get(string, string)] + if univ_pos not in ('ADJ', 'DET', 'NOUN', 'NUM', 'PRON', 'PROPN', 'VERB'): # Skip unchangeable pos return [string.lower()] @@ -39,7 +42,7 @@ class RussianLemmatizer(Lemmatizer): if not len(filtered_analyses): return [string.lower()] - if morphology is None: + if morphology is None or (len(morphology) == 1 and POS in morphology): return list(set([analysis.normal_form for analysis in filtered_analyses])) if univ_pos in ('ADJ', 'DET', 'NOUN', 'PROPN'): @@ -55,7 +58,8 @@ class RussianLemmatizer(Lemmatizer): for analysis in analyses: _, analysis_morph = oc2ud(str(analysis.tag)) for feature in features_to_compare: - if feature in morphology and morphology[feature] != analysis_morph[feature]: + if (feature in morphology and feature in analysis_morph + and morphology[feature] != analysis_morph[feature]): break else: filtered_analyses.append(analysis) @@ -76,6 +80,7 @@ class RussianLemmatizer(Lemmatizer): NUM: 'NUM', PRON: 'PRON', PROPN: 'PROPN', + PUNCT: 'PUNCT', VERB: 'VERB' } if univ_pos in symbols_to_str: @@ -86,7 +91,6 @@ class RussianLemmatizer(Lemmatizer): # TODO raise NotImplementedError - # ('ADJ', 'DET', 'NOUN', 'NUM', 'PRON', 'PROPN', 'VERB'): def det(self, string, morphology=None): return self(string, 'det', morphology) @@ -227,6 +231,7 @@ def oc2ud(oc_tag): return pos, morphology -if __name__ == '__main__': - l = RussianLemmatizer() - print(l.noun('гвоздики', {'Gender': 'Fem'})) +PUNCT_RULES = { + "«": "\"", + "»": "\"" +} diff --git a/spacy/lang/ru/norm_exceptions.py b/spacy/lang/ru/norm_exceptions.py index 6c3a5007c..53f48a8d8 100644 --- a/spacy/lang/ru/norm_exceptions.py +++ b/spacy/lang/ru/norm_exceptions.py @@ -5,22 +5,15 @@ from __future__ import unicode_literals _exc = { # Slang 'прив': 'привет', - - # Weekdays abbreviations - "пн.": "понедельник", - "вт.": "вторник", - "ср.": "среда", - "чт.": "четверг", - "пт.": "пятница", - "сб.": "суббота", - "вс.": "воскресенье", - - # Months abbreviations - "янв.": "январь", - "фев.": "февраль", - "мар.": "март", - "апр.": "апрель", - + 'ща': 'сейчас', + 'спс': 'спасибо', + 'пжлст': 'пожалуйста', + 'плиз': 'пожалуйста', + 'лан': 'ладно', + 'ясн': 'ясно', + 'всм': 'всмысле', + 'хош': 'хочешь', + 'оч': 'очень' } @@ -29,6 +22,3 @@ NORM_EXCEPTIONS = {} for string, norm in _exc.items(): NORM_EXCEPTIONS[string] = norm NORM_EXCEPTIONS[string.title()] = norm - if string.endswith('.'): - NORM_EXCEPTIONS[string[:-1]] = norm - NORM_EXCEPTIONS[string.title()[:-1]] = norm diff --git a/spacy/lang/ru/tag_map.py b/spacy/lang/ru/tag_map.py new file mode 100644 index 000000000..1369a9dbf --- /dev/null +++ b/spacy/lang/ru/tag_map.py @@ -0,0 +1,731 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...symbols import ( + POS, PUNCT, SYM, ADJ, NUM, DET, ADV, ADP, X, VERB, NOUN, PROPN, PART, INTJ, SPACE, PRON, SCONJ, AUX, CONJ, CCONJ +) + +TAG_MAP = { + 'ADJ__Animacy=Anim|Case=Acc|Degree=Pos|Gender=Masc|Number=Sing': {POS: ADJ, 'Animacy': 'Anim', 'Case': 'Acc', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Animacy=Anim|Case=Acc|Degree=Pos|Number=Plur': {POS: ADJ, 'Animacy': 'Anim', 'Case': 'Acc', 'Degree': 'Pos', 'Number': 'Plur'}, + 'ADJ__Animacy=Anim|Case=Acc|Degree=Sup|Gender=Masc|Number=Sing': {POS: ADJ, 'Animacy': 'Anim', 'Case': 'Acc', 'Degree': 'Sup', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Animacy=Anim|Case=Nom|Degree=Pos|Number=Plur': {POS: ADJ, 'Animacy': 'Anim', 'Case': 'Nom', 'Degree': 'Pos', 'Number': 'Plur'}, + 'ADJ__Animacy=Inan|Case=Acc|Degree=Pos|Gender=Masc|Number=Sing': {POS: ADJ, 'Animacy': 'Inan', 'Case': 'Acc', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Animacy=Inan|Case=Acc|Degree=Pos|Gender=Neut|Number=Sing': {POS: ADJ, 'Animacy': 'Inan', 'Case': 'Acc', 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Animacy=Inan|Case=Acc|Degree=Pos|Number=Plur': {POS: ADJ, 'Animacy': 'Inan', 'Case': 'Acc', 'Degree': 'Pos', 'Number': 'Plur'}, + 'ADJ__Animacy=Inan|Case=Acc|Degree=Sup|Gender=Masc|Number=Sing': {POS: ADJ, 'Animacy': 'Inan', 'Case': 'Acc', 'Degree': 'Sup', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Animacy=Inan|Case=Acc|Degree=Sup|Number=Plur': {POS: ADJ, 'Animacy': 'Inan', 'Case': 'Acc', 'Degree': 'Sup', 'Number': 'Plur'}, + 'ADJ__Animacy=Inan|Case=Acc|Gender=Fem|Number=Sing': {POS: ADJ, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Animacy=Inan|Case=Nom|Degree=Pos|Gender=Fem|Number=Sing': {POS: ADJ, 'Animacy': 'Inan', 'Case': 'Nom', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Acc|Degree=Pos|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Acc', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Acc|Degree=Pos|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Acc', 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Acc|Degree=Sup|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Acc', 'Degree': 'Sup', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Acc|Degree=Sup|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Acc', 'Degree': 'Sup', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Dat|Degree=Pos|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Dat', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Dat|Degree=Pos|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Dat', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Dat|Degree=Pos|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Dat', 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Dat|Degree=Pos|Number=Plur': {POS: ADJ, 'Case': 'Dat', 'Degree': 'Pos', 'Number': 'Plur'}, + 'ADJ__Case=Dat|Degree=Sup|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Dat', 'Degree': 'Sup', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Dat|Degree=Sup|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Dat', 'Degree': 'Sup', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Dat|Degree=Sup|Number=Plur': {POS: ADJ, 'Case': 'Dat', 'Degree': 'Sup', 'Number': 'Plur'}, + 'ADJ__Case=Gen|Degree=Pos|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Gen|Degree=Pos|Gender=Fem|Number=Sing|Variant=Short': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing', 'Variant': 'Short'}, + 'ADJ__Case=Gen|Degree=Pos|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Gen|Degree=Pos|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Gen|Degree=Pos|Number=Plur': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Pos', 'Number': 'Plur'}, + 'ADJ__Case=Gen|Degree=Sup|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Sup', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Gen|Degree=Sup|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Sup', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Gen|Degree=Sup|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Sup', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Gen|Degree=Sup|Number=Plur': {POS: ADJ, 'Case': 'Gen', 'Degree': 'Sup', 'Number': 'Plur'}, + 'ADJ__Case=Ins|Degree=Pos|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Ins', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Ins|Degree=Pos|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Ins', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Ins|Degree=Pos|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Ins', 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Ins|Degree=Pos|Number=Plur': {POS: ADJ, 'Case': 'Ins', 'Degree': 'Pos', 'Number': 'Plur'}, + 'ADJ__Case=Ins|Degree=Sup|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Ins', 'Degree': 'Sup', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Ins|Degree=Sup|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Ins', 'Degree': 'Sup', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Ins|Degree=Sup|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Ins', 'Degree': 'Sup', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Ins|Degree=Sup|Number=Plur': {POS: ADJ, 'Case': 'Ins', 'Degree': 'Sup', 'Number': 'Plur'}, + 'ADJ__Case=Loc|Degree=Pos|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Loc', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Loc|Degree=Pos|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Loc', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Loc|Degree=Pos|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Loc', 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Loc|Degree=Pos|Number=Plur': {POS: ADJ, 'Case': 'Loc', 'Degree': 'Pos', 'Number': 'Plur'}, + 'ADJ__Case=Loc|Degree=Sup|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Loc', 'Degree': 'Sup', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Loc|Degree=Sup|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Loc', 'Degree': 'Sup', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Loc|Degree=Sup|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Loc', 'Degree': 'Sup', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Loc|Degree=Sup|Number=Plur': {POS: ADJ, 'Case': 'Loc', 'Degree': 'Sup', 'Number': 'Plur'}, + 'ADJ__Case=Nom|Degree=Pos|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Nom', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Nom|Degree=Pos|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Nom', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Nom|Degree=Pos|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Nom', 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Nom|Degree=Pos|Number=Plur': {POS: ADJ, 'Case': 'Nom', 'Degree': 'Pos', 'Number': 'Plur'}, + 'ADJ__Case=Nom|Degree=Sup|Gender=Fem|Number=Sing': {POS: ADJ, 'Case': 'Nom', 'Degree': 'Sup', 'Gender': 'Fem', 'Number': 'Sing'}, + 'ADJ__Case=Nom|Degree=Sup|Gender=Masc|Number=Sing': {POS: ADJ, 'Case': 'Nom', 'Degree': 'Sup', 'Gender': 'Masc', 'Number': 'Sing'}, + 'ADJ__Case=Nom|Degree=Sup|Gender=Neut|Number=Sing': {POS: ADJ, 'Case': 'Nom', 'Degree': 'Sup', 'Gender': 'Neut', 'Number': 'Sing'}, + 'ADJ__Case=Nom|Degree=Sup|Number=Plur': {POS: ADJ, 'Case': 'Nom', 'Degree': 'Sup', 'Number': 'Plur'}, + 'ADJ__Degree=Cmp': {POS: ADJ, 'Degree': 'Cmp'}, + 'ADJ__Degree=Pos': {POS: ADJ, 'Degree': 'Pos'}, + 'ADJ__Degree=Pos|Gender=Fem|Number=Sing|Variant=Short': {POS: ADJ, 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing', 'Variant': 'Short'}, + 'ADJ__Degree=Pos|Gender=Masc|Number=Sing|Variant=Short': {POS: ADJ, 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing', 'Variant': 'Short'}, + 'ADJ__Degree=Pos|Gender=Neut|Number=Sing|Variant=Short': {POS: ADJ, 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing', 'Variant': 'Short'}, + 'ADJ__Degree=Pos|Number=Plur|Variant=Short': {POS: ADJ, 'Degree': 'Pos', 'Number': 'Plur', 'Variant': 'Short'}, + 'ADJ__Foreign=Yes': {POS: ADJ, 'Foreign': 'Yes'}, + 'ADJ___': {POS: ADJ}, + 'ADP___': {POS: ADP}, + 'ADV__Degree=Cmp': {POS: ADV, 'Degree': 'Cmp'}, + 'ADV__Degree=Pos': {POS: ADV, 'Degree': 'Pos'}, + 'ADV__Polarity=Neg': {POS: ADV, 'Polarity': 'Neg'}, + 'AUX__Aspect=Imp|Case=Loc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Case=Nom|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Case=Nom|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Gender': 'Fem', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Gender': 'Masc', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Gender=Neut|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Gender': 'Neut', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Imp', 'Number': 'Plur', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Imp', 'Number': 'Sing', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Ind|Number=Plur|Person=1|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '1', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Ind|Number=Plur|Person=2|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '2', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '3', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Ind|Number=Plur|Tense=Past|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '1', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Ind|Number=Sing|Person=2|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '2', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '3', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|Tense=Pres|VerbForm=Conv|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'Tense': 'Pres', 'VerbForm': 'Conv', 'Voice': 'Act'}, + 'AUX__Aspect=Imp|VerbForm=Inf|Voice=Act': {POS: AUX, 'Aspect': 'Imp', 'VerbForm': 'Inf', 'Voice': 'Act'}, + 'CCONJ___': {POS: CCONJ}, + 'DET__Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing': {POS: DET, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'DET__Animacy=Inan|Case=Acc|Gender=Neut|Number=Sing': {POS: DET, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'DET__Animacy=Inan|Case=Gen|Gender=Fem|Number=Sing': {POS: DET, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing'}, + 'DET__Animacy=Inan|Case=Gen|Number=Plur': {POS: DET, 'Animacy': 'Inan', 'Case': 'Gen', 'Number': 'Plur'}, + 'DET__Case=Acc|Degree=Pos|Number=Plur': {POS: DET, 'Case': 'Acc', 'Degree': 'Pos', 'Number': 'Plur'}, + 'DET__Case=Acc|Gender=Fem|Number=Sing': {POS: DET, 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'DET__Case=Acc|Gender=Masc|Number=Sing': {POS: DET, 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'DET__Case=Acc|Gender=Neut|Number=Sing': {POS: DET, 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'DET__Case=Acc|Number=Plur': {POS: DET, 'Case': 'Acc', 'Number': 'Plur'}, + 'DET__Case=Dat|Gender=Fem|Number=Sing': {POS: DET, 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing'}, + 'DET__Case=Dat|Gender=Masc|Number=Plur': {POS: DET, 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Plur'}, + 'DET__Case=Dat|Gender=Masc|Number=Sing': {POS: DET, 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing'}, + 'DET__Case=Dat|Gender=Neut|Number=Sing': {POS: DET, 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing'}, + 'DET__Case=Dat|Number=Plur': {POS: DET, 'Case': 'Dat', 'Number': 'Plur'}, + 'DET__Case=Gen|Gender=Fem|Number=Sing': {POS: DET, 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing'}, + 'DET__Case=Gen|Gender=Masc|Number=Sing': {POS: DET, 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing'}, + 'DET__Case=Gen|Gender=Neut|Number=Sing': {POS: DET, 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing'}, + 'DET__Case=Gen|Number=Plur': {POS: DET, 'Case': 'Gen', 'Number': 'Plur'}, + 'DET__Case=Ins|Gender=Fem|Number=Sing': {POS: DET, 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing'}, + 'DET__Case=Ins|Gender=Masc|Number=Sing': {POS: DET, 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing'}, + 'DET__Case=Ins|Gender=Neut|Number=Sing': {POS: DET, 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing'}, + 'DET__Case=Ins|Number=Plur': {POS: DET, 'Case': 'Ins', 'Number': 'Plur'}, + 'DET__Case=Loc|Gender=Fem|Number=Sing': {POS: DET, 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'DET__Case=Loc|Gender=Masc|Number=Sing': {POS: DET, 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'DET__Case=Loc|Gender=Neut|Number=Sing': {POS: DET, 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'DET__Case=Loc|Number=Plur': {POS: DET, 'Case': 'Loc', 'Number': 'Plur'}, + 'DET__Case=Nom|Gender=Fem|Number=Sing': {POS: DET, 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing'}, + 'DET__Case=Nom|Gender=Masc|Number=Plur': {POS: DET, 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Plur'}, + 'DET__Case=Nom|Gender=Masc|Number=Sing': {POS: DET, 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing'}, + 'DET__Case=Nom|Gender=Neut|Number=Sing': {POS: DET, 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing'}, + 'DET__Case=Nom|Number=Plur': {POS: DET, 'Case': 'Nom', 'Number': 'Plur'}, + 'DET__Gender=Masc|Number=Sing': {POS: DET, 'Gender': 'Masc', 'Number': 'Sing'}, + 'INTJ___': {POS: INTJ}, + 'NOUN__Animacy=Anim|Case=Acc|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Acc|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Acc|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Acc|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Acc|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Acc|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Acc', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Dat|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Dat|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Dat|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Dat|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Dat|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Dat|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Dat|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Dat', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Gen|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Gen|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Gen|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Gen|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Gen|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Gen|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Gen|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Gen', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Ins|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Ins|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Ins|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Ins|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Ins|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Ins|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Ins|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Ins', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Loc|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Loc|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Loc|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Loc|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Loc|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Loc|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Loc|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Loc', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Nom|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Nom|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Nom|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Nom|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Nom|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Anim|Case=Nom|Number=Plur': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Nom', 'Number': 'Plur'}, + 'NOUN__Animacy=Anim|Case=Voc|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Anim', 'Case': 'Voc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Acc|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Acc|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Acc|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Acc|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Acc|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Acc|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Acc', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Dat|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Dat|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Dat|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Dat|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Dat|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Dat|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Dat|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Dat', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Gen|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Gen|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Gen|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Gen|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Gen|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Gen|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Gen|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Gen', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Ins|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Ins|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Ins|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Ins|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Ins|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Ins|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Ins|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Ins', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Loc|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Loc|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Loc|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Loc|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Loc|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Loc|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Loc|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Loc', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Nom|Gender=Fem|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Nom|Gender=Fem|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Nom|Gender=Masc|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Nom|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Nom|Gender=Neut|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Nom|Gender=Neut|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Case=Nom|Number=Plur': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Nom', 'Number': 'Plur'}, + 'NOUN__Animacy=Inan|Case=Par|Gender=Masc|Number=Sing': {POS: NOUN, 'Animacy': 'Inan', 'Case': 'Par', 'Gender': 'Masc', 'Number': 'Sing'}, + 'NOUN__Animacy=Inan|Gender=Fem': {POS: NOUN, 'Animacy': 'Inan', 'Gender': 'Fem'}, + 'NOUN__Animacy=Inan|Gender=Masc': {POS: NOUN, 'Animacy': 'Inan', 'Gender': 'Masc'}, + 'NOUN__Animacy=Inan|Gender=Neut': {POS: NOUN, 'Animacy': 'Inan', 'Gender': 'Neut'}, + 'NOUN__Case=Gen|Degree=Pos|Gender=Fem|Number=Sing': {POS: NOUN, 'Case': 'Gen', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'NOUN__Foreign=Yes': {POS: NOUN, 'Foreign': 'Yes'}, + 'NOUN___': {POS: NOUN}, + 'NUM__Animacy=Anim|Case=Acc': {POS: NUM, 'Animacy': 'Anim', 'Case': 'Acc'}, + 'NUM__Animacy=Anim|Case=Acc|Gender=Fem': {POS: NUM, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Fem'}, + 'NUM__Animacy=Anim|Case=Acc|Gender=Masc': {POS: NUM, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Masc'}, + 'NUM__Animacy=Inan|Case=Acc': {POS: NUM, 'Animacy': 'Inan', 'Case': 'Acc'}, + 'NUM__Animacy=Inan|Case=Acc|Gender=Fem': {POS: NUM, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Fem'}, + 'NUM__Animacy=Inan|Case=Acc|Gender=Masc': {POS: NUM, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Masc'}, + 'NUM__Case=Acc': {POS: NUM, 'Case': 'Acc'}, + 'NUM__Case=Acc|Gender=Fem': {POS: NUM, 'Case': 'Acc', 'Gender': 'Fem'}, + 'NUM__Case=Acc|Gender=Masc': {POS: NUM, 'Case': 'Acc', 'Gender': 'Masc'}, + 'NUM__Case=Acc|Gender=Neut': {POS: NUM, 'Case': 'Acc', 'Gender': 'Neut'}, + 'NUM__Case=Dat': {POS: NUM, 'Case': 'Dat'}, + 'NUM__Case=Dat|Gender=Fem': {POS: NUM, 'Case': 'Dat', 'Gender': 'Fem'}, + 'NUM__Case=Dat|Gender=Masc': {POS: NUM, 'Case': 'Dat', 'Gender': 'Masc'}, + 'NUM__Case=Dat|Gender=Neut': {POS: NUM, 'Case': 'Dat', 'Gender': 'Neut'}, + 'NUM__Case=Gen': {POS: NUM, 'Case': 'Gen'}, + 'NUM__Case=Gen|Gender=Fem': {POS: NUM, 'Case': 'Gen', 'Gender': 'Fem'}, + 'NUM__Case=Gen|Gender=Masc': {POS: NUM, 'Case': 'Gen', 'Gender': 'Masc'}, + 'NUM__Case=Gen|Gender=Neut': {POS: NUM, 'Case': 'Gen', 'Gender': 'Neut'}, + 'NUM__Case=Ins': {POS: NUM, 'Case': 'Ins'}, + 'NUM__Case=Ins|Gender=Fem': {POS: NUM, 'Case': 'Ins', 'Gender': 'Fem'}, + 'NUM__Case=Ins|Gender=Masc': {POS: NUM, 'Case': 'Ins', 'Gender': 'Masc'}, + 'NUM__Case=Ins|Gender=Neut': {POS: NUM, 'Case': 'Ins', 'Gender': 'Neut'}, + 'NUM__Case=Loc': {POS: NUM, 'Case': 'Loc'}, + 'NUM__Case=Loc|Gender=Fem': {POS: NUM, 'Case': 'Loc', 'Gender': 'Fem'}, + 'NUM__Case=Loc|Gender=Masc': {POS: NUM, 'Case': 'Loc', 'Gender': 'Masc'}, + 'NUM__Case=Loc|Gender=Neut': {POS: NUM, 'Case': 'Loc', 'Gender': 'Neut'}, + 'NUM__Case=Nom': {POS: NUM, 'Case': 'Nom'}, + 'NUM__Case=Nom|Gender=Fem': {POS: NUM, 'Case': 'Nom', 'Gender': 'Fem'}, + 'NUM__Case=Nom|Gender=Masc': {POS: NUM, 'Case': 'Nom', 'Gender': 'Masc'}, + 'NUM__Case=Nom|Gender=Neut': {POS: NUM, 'Case': 'Nom', 'Gender': 'Neut'}, + 'NUM___': {POS: NUM}, + 'PART__Mood=Cnd': {POS: PART, 'Mood': 'Cnd'}, + 'PART__Polarity=Neg': {POS: PART, 'Polarity': 'Neg'}, + 'PART___': {POS: PART}, + 'PRON__Animacy=Anim|Case=Acc|Gender=Masc|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PRON__Animacy=Anim|Case=Acc|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Acc', 'Number': 'Plur'}, + 'PRON__Animacy=Anim|Case=Dat|Gender=Masc|Number=Sing': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PRON__Animacy=Anim|Case=Dat|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Dat', 'Number': 'Plur'}, + 'PRON__Animacy=Anim|Case=Gen|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Gen', 'Number': 'Plur'}, + 'PRON__Animacy=Anim|Case=Ins|Gender=Masc|Number=Sing': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PRON__Animacy=Anim|Case=Ins|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Ins', 'Number': 'Plur'}, + 'PRON__Animacy=Anim|Case=Loc|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Loc', 'Number': 'Plur'}, + 'PRON__Animacy=Anim|Case=Nom|Gender=Masc|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PRON__Animacy=Anim|Case=Nom|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Case': 'Nom', 'Number': 'Plur'}, + 'PRON__Animacy=Anim|Gender=Masc|Number=Plur': {POS: PRON, 'Animacy': 'Anim', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PRON__Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Case=Acc|Gender=Neut|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Case=Dat|Gender=Neut|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Case=Gen|Gender=Masc|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Case=Gen|Gender=Neut|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Case=Ins|Gender=Fem|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Case=Ins|Gender=Neut|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Case=Loc|Gender=Neut|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Case=Nom|Gender=Neut|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PRON__Animacy=Inan|Gender=Neut|Number=Sing': {POS: PRON, 'Animacy': 'Inan', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PRON__Case=Acc': {POS: PRON, 'Case': 'Acc'}, + 'PRON__Case=Acc|Gender=Fem|Number=Sing|Person=3': {POS: PRON, 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Acc|Gender=Masc|Number=Sing|Person=3': {POS: PRON, 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Acc|Gender=Neut|Number=Sing|Person=3': {POS: PRON, 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Acc|Number=Plur|Person=1': {POS: PRON, 'Case': 'Acc', 'Number': 'Plur', 'Person': '1'}, + 'PRON__Case=Acc|Number=Plur|Person=2': {POS: PRON, 'Case': 'Acc', 'Number': 'Plur', 'Person': '2'}, + 'PRON__Case=Acc|Number=Plur|Person=3': {POS: PRON, 'Case': 'Acc', 'Number': 'Plur', 'Person': '3'}, + 'PRON__Case=Acc|Number=Sing|Person=1': {POS: PRON, 'Case': 'Acc', 'Number': 'Sing', 'Person': '1'}, + 'PRON__Case=Acc|Number=Sing|Person=2': {POS: PRON, 'Case': 'Acc', 'Number': 'Sing', 'Person': '2'}, + 'PRON__Case=Dat': {POS: PRON, 'Case': 'Dat'}, + 'PRON__Case=Dat|Gender=Fem|Number=Sing|Person=3': {POS: PRON, 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Dat|Gender=Masc|Number=Sing|Person=3': {POS: PRON, 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Dat|Gender=Neut|Number=Sing|Person=3': {POS: PRON, 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Dat|Number=Plur|Person=1': {POS: PRON, 'Case': 'Dat', 'Number': 'Plur', 'Person': '1'}, + 'PRON__Case=Dat|Number=Plur|Person=2': {POS: PRON, 'Case': 'Dat', 'Number': 'Plur', 'Person': '2'}, + 'PRON__Case=Dat|Number=Plur|Person=3': {POS: PRON, 'Case': 'Dat', 'Number': 'Plur', 'Person': '3'}, + 'PRON__Case=Dat|Number=Sing|Person=1': {POS: PRON, 'Case': 'Dat', 'Number': 'Sing', 'Person': '1'}, + 'PRON__Case=Dat|Number=Sing|Person=2': {POS: PRON, 'Case': 'Dat', 'Number': 'Sing', 'Person': '2'}, + 'PRON__Case=Gen': {POS: PRON, 'Case': 'Gen'}, + 'PRON__Case=Gen|Gender=Fem|Number=Sing|Person=3': {POS: PRON, 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Gen|Gender=Masc|Number=Sing|Person=3': {POS: PRON, 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Gen|Gender=Neut|Number=Sing|Person=3': {POS: PRON, 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Gen|Number=Plur|Person=1': {POS: PRON, 'Case': 'Gen', 'Number': 'Plur', 'Person': '1'}, + 'PRON__Case=Gen|Number=Plur|Person=2': {POS: PRON, 'Case': 'Gen', 'Number': 'Plur', 'Person': '2'}, + 'PRON__Case=Gen|Number=Plur|Person=3': {POS: PRON, 'Case': 'Gen', 'Number': 'Plur', 'Person': '3'}, + 'PRON__Case=Gen|Number=Sing|Person=1': {POS: PRON, 'Case': 'Gen', 'Number': 'Sing', 'Person': '1'}, + 'PRON__Case=Gen|Number=Sing|Person=2': {POS: PRON, 'Case': 'Gen', 'Number': 'Sing', 'Person': '2'}, + 'PRON__Case=Ins': {POS: PRON, 'Case': 'Ins'}, + 'PRON__Case=Ins|Gender=Fem|Number=Sing|Person=3': {POS: PRON, 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Ins|Gender=Masc|Number=Sing|Person=3': {POS: PRON, 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Ins|Gender=Neut|Number=Sing|Person=3': {POS: PRON, 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Ins|Number=Plur|Person=1': {POS: PRON, 'Case': 'Ins', 'Number': 'Plur', 'Person': '1'}, + 'PRON__Case=Ins|Number=Plur|Person=2': {POS: PRON, 'Case': 'Ins', 'Number': 'Plur', 'Person': '2'}, + 'PRON__Case=Ins|Number=Plur|Person=3': {POS: PRON, 'Case': 'Ins', 'Number': 'Plur', 'Person': '3'}, + 'PRON__Case=Ins|Number=Sing|Person=1': {POS: PRON, 'Case': 'Ins', 'Number': 'Sing', 'Person': '1'}, + 'PRON__Case=Ins|Number=Sing|Person=2': {POS: PRON, 'Case': 'Ins', 'Number': 'Sing', 'Person': '2'}, + 'PRON__Case=Loc': {POS: PRON, 'Case': 'Loc'}, + 'PRON__Case=Loc|Gender=Fem|Number=Sing|Person=3': {POS: PRON, 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Loc|Gender=Masc|Number=Sing|Person=3': {POS: PRON, 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Loc|Gender=Neut|Number=Sing|Person=3': {POS: PRON, 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Loc|Number=Plur|Person=1': {POS: PRON, 'Case': 'Loc', 'Number': 'Plur', 'Person': '1'}, + 'PRON__Case=Loc|Number=Plur|Person=2': {POS: PRON, 'Case': 'Loc', 'Number': 'Plur', 'Person': '2'}, + 'PRON__Case=Loc|Number=Plur|Person=3': {POS: PRON, 'Case': 'Loc', 'Number': 'Plur', 'Person': '3'}, + 'PRON__Case=Loc|Number=Sing|Person=1': {POS: PRON, 'Case': 'Loc', 'Number': 'Sing', 'Person': '1'}, + 'PRON__Case=Loc|Number=Sing|Person=2': {POS: PRON, 'Case': 'Loc', 'Number': 'Sing', 'Person': '2'}, + 'PRON__Case=Nom': {POS: PRON, 'Case': 'Nom'}, + 'PRON__Case=Nom|Gender=Fem|Number=Sing|Person=3': {POS: PRON, 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Nom|Gender=Masc|Number=Sing|Person=3': {POS: PRON, 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Nom|Gender=Neut|Number=Sing|Person=3': {POS: PRON, 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Person': '3'}, + 'PRON__Case=Nom|Number=Plur|Person=1': {POS: PRON, 'Case': 'Nom', 'Number': 'Plur', 'Person': '1'}, + 'PRON__Case=Nom|Number=Plur|Person=2': {POS: PRON, 'Case': 'Nom', 'Number': 'Plur', 'Person': '2'}, + 'PRON__Case=Nom|Number=Plur|Person=3': {POS: PRON, 'Case': 'Nom', 'Number': 'Plur', 'Person': '3'}, + 'PRON__Case=Nom|Number=Sing|Person=1': {POS: PRON, 'Case': 'Nom', 'Number': 'Sing', 'Person': '1'}, + 'PRON__Case=Nom|Number=Sing|Person=2': {POS: PRON, 'Case': 'Nom', 'Number': 'Sing', 'Person': '2'}, + 'PRON__Number=Sing|Person=1': {POS: PRON, 'Number': 'Sing', 'Person': '1'}, + 'PRON___': {POS: PRON}, + 'PROPN__Animacy=Anim|Case=Acc|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Acc|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Acc|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Acc|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Dat|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Dat|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Dat|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Dat|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Dat|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Gen|Foreign=Yes|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Gen', 'Foreign': 'Yes', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Gen|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Gen|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Gen|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Gen|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Ins|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Ins|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Ins|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Ins|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Loc|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Loc|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Loc|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Nom|Foreign=Yes|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Nom', 'Foreign': 'Yes', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Nom|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Nom|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Nom|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Case=Nom|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Anim|Case=Voc|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Case': 'Voc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Anim|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Anim', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Acc|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Acc|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Acc|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Acc|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Acc|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Acc|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Acc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Acc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Dat|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Dat|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Dat|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Dat|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Dat|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Dat|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Dat|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Dat', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Gen|Foreign=Yes|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Gen', 'Foreign': 'Yes', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Gen|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Gen|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Gen|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Gen|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Gen|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Gen|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Gen|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Gen', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Ins|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Ins|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Ins|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Ins|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Ins|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Ins|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Ins|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Ins', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Loc|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Loc|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Loc|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Loc|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Loc|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Loc|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Loc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Loc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Nom|Foreign=Yes|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Foreign': 'Yes', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Nom|Foreign=Yes|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Foreign': 'Yes', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Nom|Foreign=Yes|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Foreign': 'Yes', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Nom|Gender=Fem|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Nom|Gender=Fem|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Nom|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Nom|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Nom|Gender=Neut|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Nom|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Case=Nom|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Nom', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Case=Par|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Case': 'Par', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Gender=Fem': {POS: PROPN, 'Animacy': 'Inan', 'Gender': 'Fem'}, + 'PROPN__Animacy=Inan|Gender=Masc': {POS: PROPN, 'Animacy': 'Inan', 'Gender': 'Masc'}, + 'PROPN__Animacy=Inan|Gender=Masc|Number=Plur': {POS: PROPN, 'Animacy': 'Inan', 'Gender': 'Masc', 'Number': 'Plur'}, + 'PROPN__Animacy=Inan|Gender=Masc|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Animacy=Inan|Gender=Neut|Number=Sing': {POS: PROPN, 'Animacy': 'Inan', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Case=Acc|Degree=Pos|Gender=Fem|Number=Sing': {POS: PROPN, 'Case': 'Acc', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Case=Dat|Degree=Pos|Gender=Masc|Number=Sing': {POS: PROPN, 'Case': 'Dat', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Case=Ins|Degree=Pos|Gender=Fem|Number=Sing': {POS: PROPN, 'Case': 'Ins', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Case=Ins|Degree=Pos|Number=Plur': {POS: PROPN, 'Case': 'Ins', 'Degree': 'Pos', 'Number': 'Plur'}, + 'PROPN__Case=Nom|Degree=Pos|Gender=Fem|Number=Sing': {POS: PROPN, 'Case': 'Nom', 'Degree': 'Pos', 'Gender': 'Fem', 'Number': 'Sing'}, + 'PROPN__Case=Nom|Degree=Pos|Gender=Masc|Number=Sing': {POS: PROPN, 'Case': 'Nom', 'Degree': 'Pos', 'Gender': 'Masc', 'Number': 'Sing'}, + 'PROPN__Case=Nom|Degree=Pos|Gender=Neut|Number=Sing': {POS: PROPN, 'Case': 'Nom', 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing'}, + 'PROPN__Case=Nom|Degree=Pos|Number=Plur': {POS: PROPN, 'Case': 'Nom', 'Degree': 'Pos', 'Number': 'Plur'}, + 'PROPN__Degree=Pos|Gender=Neut|Number=Sing|Variant=Short': {POS: PROPN, 'Degree': 'Pos', 'Gender': 'Neut', 'Number': 'Sing', 'Variant': 'Short'}, + 'PROPN__Degree=Pos|Number=Plur|Variant=Short': {POS: PROPN, 'Degree': 'Pos', 'Number': 'Plur', 'Variant': 'Short'}, + 'PROPN__Foreign=Yes': {POS: PROPN, 'Foreign': 'Yes'}, + 'PROPN__Number=Sing': {POS: PROPN, 'Number': 'Sing'}, + 'PROPN___': {POS: PROPN}, + 'PUNCT___': {POS: PUNCT}, + 'SCONJ__Mood=Cnd': {POS: SCONJ, 'Mood': 'Cnd'}, + 'SCONJ___': {POS: SCONJ}, + 'SYM___': {POS: SYM}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Anim|Aspect=Imp|Case=Acc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Anim|Aspect=Perf|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Anim|Aspect=Perf|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Anim|Aspect=Perf|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Anim|Aspect=Perf|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Perf', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Anim|Aspect=Perf|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Perf', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Anim|Aspect=Perf|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Anim', 'Aspect': 'Perf', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Inan|Aspect=Imp|Case=Acc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Imp', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Inan|Aspect=Perf|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Inan|Aspect=Perf|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Inan|Aspect=Perf|Case=Acc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Animacy=Inan|Aspect=Perf|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Perf', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Animacy=Inan|Aspect=Perf|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Perf', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Animacy=Inan|Aspect=Perf|Case=Acc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Animacy': 'Inan', 'Aspect': 'Perf', 'Case': 'Acc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Acc|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Dat|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Dat|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Dat|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Dat|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Dat|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Dat|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Dat|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Gen|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Gen|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Gen|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Gen|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Gen|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Gen|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Gen|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Ins|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Ins|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Ins|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Ins|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Ins|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Ins|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Ins', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Loc|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Loc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Loc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Loc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Loc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Loc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Loc|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Fem|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Masc|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Nom|Gender=Neut|Number=Sing|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Nom|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Nom|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Nom|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Case=Nom|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Case=Nom|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Case=Nom|Number=Plur|Tense=Pres|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Pres', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Fem', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Fem', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Fem', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Fem|Number=Sing|Tense=Past|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Fem|Number=Sing|Tense=Pres|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Pres', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Masc', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Masc', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Masc', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Masc|Number=Sing|Tense=Past|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Masc|Number=Sing|Tense=Pres|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Pres', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Neut|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Neut', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Gender=Neut|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Neut', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Gender=Neut|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Neut', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Neut|Number=Sing|Tense=Past|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Gender=Neut|Number=Sing|Tense=Pres|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Pres', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Imp', 'Number': 'Plur', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Imp', 'Number': 'Plur', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Imp', 'Number': 'Sing', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Imp', 'Number': 'Sing', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Person=1|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '1', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Person=1|Tense=Pres|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '1', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Person=2|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '2', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Person=2|Tense=Pres|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '2', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '3', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '3', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Tense=Pres|VerbForm=Fin|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '3', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Tense=Past|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Tense=Past|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Plur|Tense=Past|VerbForm=Fin|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '1', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Tense=Pres|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '1', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Sing|Person=2|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '2', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Sing|Person=2|Tense=Pres|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '2', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '3', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '3', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '3', 'Tense': 'Pres', 'VerbForm': 'Fin', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Number=Plur|Tense=Past|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Number': 'Plur', 'Tense': 'Past', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Number=Plur|Tense=Pres|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Number': 'Plur', 'Tense': 'Pres', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|Tense=Past|VerbForm=Conv|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Tense': 'Past', 'VerbForm': 'Conv', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Tense=Pres|VerbForm=Conv|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'Tense': 'Pres', 'VerbForm': 'Conv', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|Tense=Pres|VerbForm=Conv|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'Tense': 'Pres', 'VerbForm': 'Conv', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|Tense=Pres|VerbForm=Conv|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'Tense': 'Pres', 'VerbForm': 'Conv', 'Voice': 'Pass'}, + 'VERB__Aspect=Imp|VerbForm=Inf|Voice=Act': {POS: VERB, 'Aspect': 'Imp', 'VerbForm': 'Inf', 'Voice': 'Act'}, + 'VERB__Aspect=Imp|VerbForm=Inf|Voice=Mid': {POS: VERB, 'Aspect': 'Imp', 'VerbForm': 'Inf', 'Voice': 'Mid'}, + 'VERB__Aspect=Imp|VerbForm=Inf|Voice=Pass': {POS: VERB, 'Aspect': 'Imp', 'VerbForm': 'Inf', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Acc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Acc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Acc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Acc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Acc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Acc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Acc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Dat|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Dat|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Dat|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Dat|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Dat', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Gen|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Gen|Number=Plur|Tense=Fut|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Fut', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Gen|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Gen|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Gen|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Gen', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Ins|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Ins|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Ins|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Ins|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Ins', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Loc|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Loc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Loc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Loc|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Loc', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Fem|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Nom|Gender=Neut|Number=Sing|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Case=Nom|Number=Plur|Tense=Past|VerbForm=Part|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Case=Nom|Number=Plur|Tense=Past|VerbForm=Part|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Case=Nom|Number=Plur|Tense=Past|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Case': 'Nom', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Fem', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Fem', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Gender=Fem|Number=Sing|Tense=Past|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Fem', 'Number': 'Sing', 'Tense': 'Past', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Masc', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Masc', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Gender=Masc|Number=Sing|Tense=Past|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Masc', 'Number': 'Sing', 'Tense': 'Past', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Gender=Neut|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Neut', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Gender=Neut|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Neut', 'Mood': 'Ind', 'Number': 'Sing', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Gender=Neut|Number=Sing|Tense=Past|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Gender': 'Neut', 'Number': 'Sing', 'Tense': 'Past', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Mood=Imp|Number=Plur|Person=1|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Imp', 'Number': 'Plur', 'Person': '1', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Imp', 'Number': 'Plur', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Imp', 'Number': 'Plur', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Imp', 'Number': 'Sing', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Imp', 'Number': 'Sing', 'Person': '2', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Person=1|Tense=Fut|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '1', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Person=1|Tense=Fut|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '1', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Person=2|Tense=Fut|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '2', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Person=2|Tense=Fut|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '2', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Person=3|Tense=Fut|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '3', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Person=3|Tense=Fut|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '3', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Person=3|Tense=Fut|VerbForm=Fin|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Person': '3', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Tense=Past|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Plur|Tense=Past|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Plur', 'Tense': 'Past', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Sing|Person=1|Tense=Fut|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '1', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Sing|Person=1|Tense=Fut|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '1', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Sing|Person=2|Tense=Fut|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '2', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Sing|Person=2|Tense=Fut|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '2', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Tense=Fut|VerbForm=Fin|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '3', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Tense=Fut|VerbForm=Fin|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Mood': 'Ind', 'Number': 'Sing', 'Person': '3', 'Tense': 'Fut', 'VerbForm': 'Fin', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|Number=Plur|Tense=Past|Variant=Short|VerbForm=Part|Voice=Pass': {POS: VERB, 'Aspect': 'Perf', 'Number': 'Plur', 'Tense': 'Past', 'Variant': 'Short', 'VerbForm': 'Part', 'Voice': 'Pass'}, + 'VERB__Aspect=Perf|Tense=Past|VerbForm=Conv|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'Tense': 'Past', 'VerbForm': 'Conv', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|Tense=Past|VerbForm=Conv|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'Tense': 'Past', 'VerbForm': 'Conv', 'Voice': 'Mid'}, + 'VERB__Aspect=Perf|VerbForm=Inf|Voice=Act': {POS: VERB, 'Aspect': 'Perf', 'VerbForm': 'Inf', 'Voice': 'Act'}, + 'VERB__Aspect=Perf|VerbForm=Inf|Voice=Mid': {POS: VERB, 'Aspect': 'Perf', 'VerbForm': 'Inf', 'Voice': 'Mid'}, + 'VERB__Voice=Act': {POS: VERB, 'Voice': 'Act'}, + 'VERB___': {POS: VERB}, + 'X__Foreign=Yes': {POS: X, 'Foreign': 'Yes'}, + 'X___': {POS: X}, +} diff --git a/spacy/lang/ru/tokenizer_exceptions.py b/spacy/lang/ru/tokenizer_exceptions.py index 707dd388c..b9a8e1e6e 100644 --- a/spacy/lang/ru/tokenizer_exceptions.py +++ b/spacy/lang/ru/tokenizer_exceptions.py @@ -1,9 +1,68 @@ # encoding: utf8 from __future__ import unicode_literals -from ...symbols import ORTH, LEMMA +from ...symbols import ORTH, LEMMA, NORM -TOKENIZER_EXCEPTIONS = { +_exc = {} -} +_abbrev_exc = [ + # Weekdays abbreviations + {ORTH: "пн", LEMMA: "понедельник", NORM: "понедельник"}, + {ORTH: "вт", LEMMA: "вторник", NORM: "вторник"}, + {ORTH: "ср", LEMMA: "среда", NORM: "среда"}, + {ORTH: "чт", LEMMA: "четверг", NORM: "четверг"}, + {ORTH: "чтв", LEMMA: "четверг", NORM: "четверг"}, + {ORTH: "пт", LEMMA: "пятница", NORM: "пятница"}, + {ORTH: "сб", LEMMA: "суббота", NORM: "суббота"}, + {ORTH: "сбт", LEMMA: "суббота", NORM: "суббота"}, + {ORTH: "вс", LEMMA: "воскресенье", NORM: "воскресенье"}, + {ORTH: "вскр", LEMMA: "воскресенье", NORM: "воскресенье"}, + {ORTH: "воскр", LEMMA: "воскресенье", NORM: "воскресенье"}, + + # Months abbreviations + {ORTH: "янв", LEMMA: "январь", NORM: "январь"}, + {ORTH: "фев", LEMMA: "февраль", NORM: "февраль"}, + {ORTH: "февр", LEMMA: "февраль", NORM: "февраль"}, + {ORTH: "мар", LEMMA: "март", NORM: "март"}, + # {ORTH: "март", LEMMA: "март", NORM: "март"}, + {ORTH: "мрт", LEMMA: "март", NORM: "март"}, + {ORTH: "апр", LEMMA: "апрель", NORM: "апрель"}, + # {ORTH: "май", LEMMA: "май", NORM: "май"}, + {ORTH: "июн", LEMMA: "июнь", NORM: "июнь"}, + # {ORTH: "июнь", LEMMA: "июнь", NORM: "июнь"}, + {ORTH: "июл", LEMMA: "июль", NORM: "июль"}, + # {ORTH: "июль", LEMMA: "июль", NORM: "июль"}, + {ORTH: "авг", LEMMA: "август", NORM: "август"}, + {ORTH: "сен", LEMMA: "сентябрь", NORM: "сентябрь"}, + {ORTH: "сент", LEMMA: "сентябрь", NORM: "сентябрь"}, + {ORTH: "окт", LEMMA: "октябрь", NORM: "октябрь"}, + {ORTH: "октб", LEMMA: "октябрь", NORM: "октябрь"}, + {ORTH: "ноя", LEMMA: "ноябрь", NORM: "ноябрь"}, + {ORTH: "нояб", LEMMA: "ноябрь", NORM: "ноябрь"}, + {ORTH: "нбр", LEMMA: "ноябрь", NORM: "ноябрь"}, + {ORTH: "дек", LEMMA: "декабрь", NORM: "декабрь"}, +] + + +for abbrev_desc in _abbrev_exc: + abbrev = abbrev_desc[ORTH] + for orth in (abbrev, abbrev.capitalize(), abbrev.upper()): + _exc[orth] = [{ORTH: orth, LEMMA: abbrev_desc[LEMMA], NORM: abbrev_desc[NORM]}] + _exc[orth + '.'] = [{ORTH: orth + '.', LEMMA: abbrev_desc[LEMMA], NORM: abbrev_desc[NORM]}] + + +_slang_exc = [ + {ORTH: '2к15', LEMMA: '2015', NORM: '2015'}, + {ORTH: '2к16', LEMMA: '2016', NORM: '2016'}, + {ORTH: '2к17', LEMMA: '2017', NORM: '2017'}, + {ORTH: '2к18', LEMMA: '2018', NORM: '2018'}, + {ORTH: '2к19', LEMMA: '2019', NORM: '2019'}, + {ORTH: '2к20', LEMMA: '2020', NORM: '2020'}, +] + +for slang_desc in _slang_exc: + _exc[slang_desc[ORTH]] = [slang_desc] + + +TOKENIZER_EXCEPTIONS = _exc diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py index 73a484c13..c52b1941b 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -42,7 +42,7 @@ def FR(request): @pytest.fixture() def RU(request): - return util.get_lang_class('ru') + pymorphy = pytest.importorskip('pymorphy2') #@pytest.fixture(params=_languages) diff --git a/spacy/tests/lang/ru/test_lemmatizer.py b/spacy/tests/lang/ru/test_lemmatizer.py index 345bcd971..2d9dd8b85 100644 --- a/spacy/tests/lang/ru/test_lemmatizer.py +++ b/spacy/tests/lang/ru/test_lemmatizer.py @@ -10,15 +10,15 @@ def ru_lemmatizer(RU): return RU.Defaults.create_lemmatizer() -# @pytest.mark.models('ru') -# def test_doc_lemmatization(RU): -# doc = Doc(RU.vocab, words=['мама', 'мыла', 'раму']) -# doc[0].tag_ = 'NOUN__Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing' -# doc[1].tag_ = 'VERB__Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act' -# doc[2].tag_ = 'NOUN__Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing' -# -# lemmas = [token.lemma_ for token in doc] -# assert lemmas == ['мама', 'мыть', 'рама'] +@pytest.mark.models('ru') +def test_doc_lemmatization(RU): + doc = Doc(RU.vocab, words=['мама', 'мыла', 'раму']) + doc[0].tag_ = 'NOUN__Animacy=Anim|Case=Nom|Gender=Fem|Number=Sing' + doc[1].tag_ = 'VERB__Aspect=Imp|Gender=Fem|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act' + doc[2].tag_ = 'NOUN__Animacy=Anim|Case=Acc|Gender=Fem|Number=Sing' + + lemmas = [token.lemma_ for token in doc] + assert lemmas == ['мама', 'мыть', 'рама'] @pytest.mark.models('ru') @@ -57,12 +57,12 @@ def test_ru_lemmatizer_works_with_noun_homonyms(ru_lemmatizer, text, morphology, assert ru_lemmatizer.noun(text, morphology) == [lemma] -# @pytest.mark.models('ru') -# def test_ru_lemmatizer_punct(ru_lemmatizer): -# assert ru_lemmatizer.punct('“') == ['"'] -# assert ru_lemmatizer.punct('“') == ['"'] -# -# +@pytest.mark.models('ru') +def test_ru_lemmatizer_punct(ru_lemmatizer): + assert ru_lemmatizer.punct('«') == ['"'] + assert ru_lemmatizer.punct('»') == ['"'] + + # @pytest.mark.models('ru') # def test_ru_lemmatizer_lemma_assignment(RU): # text = "А роза упала на лапу Азора." diff --git a/spacy/tests/lang/ru/test_punct.py b/spacy/tests/lang/ru/test_tokenizer.py similarity index 93% rename from spacy/tests/lang/ru/test_punct.py rename to spacy/tests/lang/ru/test_tokenizer.py index 6a689ff71..1c4d55d2d 100644 --- a/spacy/tests/lang/ru/test_punct.py +++ b/spacy/tests/lang/ru/test_tokenizer.py @@ -6,9 +6,6 @@ from __future__ import unicode_literals import pytest -from ....util import compile_prefix_regex -from ....lang.punctuation import TOKENIZER_PREFIXES - PUNCT_OPEN = ['(', '[', '{', '*'] PUNCT_CLOSE = [')', ']', '}', '*'] @@ -97,7 +94,7 @@ def test_ru_tokenizer_splits_double_end_quote(ru_tokenizer, text): @pytest.mark.parametrize('punct_open,punct_close', PUNCT_PAIRED) @pytest.mark.parametrize('text', ["Тест"]) def test_ru_tokenizer_splits_open_close_punct(ru_tokenizer, punct_open, - punct_close, text): + punct_close, text): tokens = ru_tokenizer(punct_open + text + punct_close) assert len(tokens) == 3 assert tokens[0].text == punct_open @@ -109,7 +106,7 @@ def test_ru_tokenizer_splits_open_close_punct(ru_tokenizer, punct_open, @pytest.mark.parametrize('punct_open2,punct_close2', [("`", "'")]) @pytest.mark.parametrize('text', ["Тест"]) def test_ru_tokenizer_two_diff_punct(ru_tokenizer, punct_open, punct_close, - punct_open2, punct_close2, text): + punct_open2, punct_close2, text): tokens = ru_tokenizer(punct_open2 + punct_open + text + punct_close + punct_close2) assert len(tokens) == 5 assert tokens[0].text == punct_open2 @@ -119,7 +116,7 @@ def test_ru_tokenizer_two_diff_punct(ru_tokenizer, punct_open, punct_close, assert tokens[4].text == punct_close2 -@pytest.mark.parametrize('text', [("Тест.")]) +@pytest.mark.parametrize('text', ["Тест."]) def test_ru_tokenizer_splits_trailing_dot(ru_tokenizer, text): tokens = ru_tokenizer(text) assert tokens[1].text == "." diff --git a/spacy/tests/lang/ru/test_tokenizer_exc.py b/spacy/tests/lang/ru/test_tokenizer_exc.py new file mode 100644 index 000000000..554036537 --- /dev/null +++ b/spacy/tests/lang/ru/test_tokenizer_exc.py @@ -0,0 +1,16 @@ +# coding: utf-8 +"""Test that tokenizer exceptions are parsed correctly.""" + + +from __future__ import unicode_literals + +import pytest + + +@pytest.mark.parametrize('text,norms', [("пн.", ["понедельник"]), + ("пт.", ["пятница"]), + ("дек.", ["декабрь"])]) +def test_ru_tokenizer_abbrev_exceptions(ru_tokenizer, text, norms): + tokens = ru_tokenizer(text) + assert len(tokens) == 1 + assert [token.norm_ for token in tokens] == norms From 53e7c3863796e0b18c383fbc05cb46fd66992db9 Mon Sep 17 00:00:00 2001 From: Vadim Mazaev Date: Sun, 26 Nov 2017 21:04:44 +0300 Subject: [PATCH 7/8] Fixed tests depends on pymorphy2 --- spacy/tests/conftest.py | 1 + 1 file changed, 1 insertion(+) diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py index c52b1941b..ae8401e54 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -144,6 +144,7 @@ def th_tokenizer(): @pytest.fixture def ru_tokenizer(): + pymorphy = pytest.importorskip('pymorphy2') return util.get_lang_class('ru').Defaults.create_tokenizer() From 49b4e2c158e5babb7b68073553e64c89f42afc57 Mon Sep 17 00:00:00 2001 From: Vadim Mazaev Date: Sun, 26 Nov 2017 22:14:08 +0300 Subject: [PATCH 8/8] Added contributor agreement --- .github/contributors/greenriverrus.md | 106 ++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/greenriverrus.md diff --git a/.github/contributors/greenriverrus.md b/.github/contributors/greenriverrus.md new file mode 100644 index 000000000..a7d6ba260 --- /dev/null +++ b/.github/contributors/greenriverrus.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI UG (haftungsbeschränkt)](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | --------------------| +| Name | Vadim Mazaev | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 26 November 2017 | +| GitHub username | GreenRiverRUS | +| Website (optional) | |