mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
Antti Ajanki
GitHub
parent
bc12ecb870
commit
e9c26f2ee9
|
|
@ -2,6 +2,7 @@ from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|||
from .stop_words import STOP_WORDS
|
||||
from .lex_attrs import LEX_ATTRS
|
||||
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
||||
from .syntax_iterators import SYNTAX_ITERATORS
|
||||
from ...language import Language, BaseDefaults
|
||||
|
||||
|
||||
|
|
@ -11,6 +12,7 @@ class FinnishDefaults(BaseDefaults):
|
|||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||
lex_attr_getters = LEX_ATTRS
|
||||
stop_words = STOP_WORDS
|
||||
syntax_iterators = SYNTAX_ITERATORS
|
||||
|
||||
|
||||
class Finnish(Language):
|
||||
|
|
|
|||
79
spacy/lang/fi/syntax_iterators.py
Normal file
79
spacy/lang/fi/syntax_iterators.py
Normal file
|
|
@ -0,0 +1,79 @@
|
|||
from typing import Iterator, Tuple, Union
|
||||
from ...tokens import Doc, Span
|
||||
from ...symbols import NOUN, PROPN, PRON
|
||||
from ...errors import Errors
|
||||
|
||||
|
||||
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Tuple[int, int, int]]:
|
||||
"""Detect base noun phrases from a dependency parse. Works on both Doc and Span."""
|
||||
labels = [
|
||||
"appos",
|
||||
"nsubj",
|
||||
"nsubj:cop",
|
||||
"obj",
|
||||
"obl",
|
||||
"ROOT",
|
||||
]
|
||||
extend_labels = [
|
||||
"amod",
|
||||
"compound",
|
||||
"compound:nn",
|
||||
"flat:name",
|
||||
"nmod",
|
||||
"nmod:gobj",
|
||||
"nmod:gsubj",
|
||||
"nmod:poss",
|
||||
"nummod",
|
||||
]
|
||||
|
||||
def potential_np_head(word):
|
||||
return word.pos in (NOUN, PROPN) and (
|
||||
word.dep in np_deps or word.head.pos == PRON
|
||||
)
|
||||
|
||||
doc = doclike.doc # Ensure works on both Doc and Span.
|
||||
if not doc.has_annotation("DEP"):
|
||||
raise ValueError(Errors.E029)
|
||||
|
||||
np_deps = [doc.vocab.strings[label] for label in labels]
|
||||
extend_deps = [doc.vocab.strings[label] for label in extend_labels]
|
||||
np_label = doc.vocab.strings.add("NP")
|
||||
conj_label = doc.vocab.strings.add("conj")
|
||||
|
||||
rbracket = 0
|
||||
prev_end = -1
|
||||
for i, word in enumerate(doclike):
|
||||
if i < rbracket:
|
||||
continue
|
||||
|
||||
# Is this a potential independent NP head or coordinated with
|
||||
# a NOUN that is itself an independent NP head?
|
||||
#
|
||||
# e.g. "Terveyden ja hyvinvoinnin laitos"
|
||||
if potential_np_head(word) or (
|
||||
word.dep == conj_label and potential_np_head(word.head)
|
||||
):
|
||||
# Try to extend to the left to include adjective/num
|
||||
# modifiers, compound words etc.
|
||||
lbracket = word.i
|
||||
for ldep in word.lefts:
|
||||
if ldep.dep in extend_deps:
|
||||
lbracket = ldep.left_edge.i
|
||||
break
|
||||
|
||||
# Prevent nested chunks from being produced
|
||||
if lbracket <= prev_end:
|
||||
continue
|
||||
|
||||
rbracket = word.i
|
||||
# Try to extend the span to the right to capture
|
||||
# appositions and noun modifiers
|
||||
for rdep in word.rights:
|
||||
if rdep.dep in extend_deps:
|
||||
rbracket = rdep.i
|
||||
prev_end = rbracket
|
||||
|
||||
yield lbracket, rbracket + 1, np_label
|
||||
|
||||
|
||||
SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}
|
||||
174
spacy/tests/lang/fi/test_noun_chunks.py
Normal file
174
spacy/tests/lang/fi/test_noun_chunks.py
Normal file
|
|
@ -0,0 +1,174 @@
|
|||
import pytest
|
||||
from spacy.tokens import Doc
|
||||
|
||||
|
||||
FI_NP_TEST_EXAMPLES = [
|
||||
(
|
||||
"Kaksi tyttöä potkii punaista palloa",
|
||||
["NUM", "NOUN", "VERB", "ADJ", "NOUN"],
|
||||
["nummod", "nsubj", "ROOT", "amod", "obj"],
|
||||
[1, 1, 0, 1, -2],
|
||||
["Kaksi tyttöä", "punaista palloa"],
|
||||
),
|
||||
(
|
||||
"Erittäin vaarallinen leijona karkasi kiertävän sirkuksen eläintenkesyttäjältä",
|
||||
["ADV", "ADJ", "NOUN", "VERB", "ADJ", "NOUN", "NOUN"],
|
||||
["advmod", "amod", "nsubj", "ROOT", "amod", "nmod:poss", "obl"],
|
||||
[1, 1, 1, 0, 1, 1, -3],
|
||||
["Erittäin vaarallinen leijona", "kiertävän sirkuksen eläintenkesyttäjältä"],
|
||||
),
|
||||
(
|
||||
"Leijona raidallisine tassuineen piileksii Porin kaupungin lähellä",
|
||||
["NOUN", "ADJ", "NOUN", "VERB", "PROPN", "NOUN", "ADP"],
|
||||
["nsubj", "amod", "nmod", "ROOT", "nmod:poss", "obl", "case"],
|
||||
[3, 1, -2, 0, 1, -2, -1],
|
||||
["Leijona raidallisine tassuineen", "Porin kaupungin"],
|
||||
),
|
||||
(
|
||||
"Lounaalla nautittiin salaattia, maukasta kanaa ja raikasta vettä",
|
||||
["NOUN", "VERB", "NOUN", "PUNCT", "ADJ", "NOUN", "CCONJ", "ADJ", "NOUN"],
|
||||
["obl", "ROOT", "obj", "punct", "amod", "conj", "cc", "amod", "conj"],
|
||||
[1, 0, -1, 2, 1, -3, 2, 1, -6],
|
||||
["Lounaalla", "salaattia", "maukasta kanaa", "raikasta vettä"],
|
||||
),
|
||||
(
|
||||
"Minua houkuttaa maalle muuttaminen talven jälkeen",
|
||||
["PRON", "VERB", "NOUN", "NOUN", "NOUN", "ADP"],
|
||||
["obj", "ROOT", "nmod", "nsubj", "obl", "case"],
|
||||
[1, 0, 1, -2, -3, -1],
|
||||
["maalle muuttaminen", "talven"],
|
||||
),
|
||||
(
|
||||
"Päivän kohokohta oli vierailu museossa kummilasten kanssa",
|
||||
["NOUN", "NOUN", "AUX", "NOUN", "NOUN", "NOUN", "ADP"],
|
||||
["nmod:poss", "nsubj:cop", "cop", "ROOT", "nmod", "obl", "case"],
|
||||
[1, 2, 1, 0, -1, -2, -1],
|
||||
["Päivän kohokohta", "vierailu museossa", "kummilasten"],
|
||||
),
|
||||
(
|
||||
"Yrittäjät maksoivat tuomioistuimen määräämät korvaukset",
|
||||
["NOUN", "VERB", "NOUN", "VERB", "NOUN"],
|
||||
["nsubj", "ROOT", "nsubj", "acl", "obj"],
|
||||
[1, 0, 1, 1, -3],
|
||||
["Yrittäjät", "tuomioistuimen", "korvaukset"],
|
||||
),
|
||||
(
|
||||
"Julkisoikeudelliset tai niihin rinnastettavat saatavat ovat suoraan ulosottokelpoisia",
|
||||
["ADJ", "CCONJ", "PRON", "VERB", "NOUN", "AUX", "ADV", "NOUN"],
|
||||
["amod", "cc", "obl", "acl", "nsubj:cop", "cop", "advmod", "ROOT"],
|
||||
[4, 3, 1, 1, 3, 2, 1, 0],
|
||||
["Julkisoikeudelliset tai niihin rinnastettavat saatavat", "ulosottokelpoisia"],
|
||||
),
|
||||
(
|
||||
"Se oli ala-arvoista käytöstä kaikilta oppilailta, myös valvojaoppilailta",
|
||||
["PRON", "AUX", "ADJ", "NOUN", "PRON", "NOUN", "PUNCT", "ADV", "NOUN"],
|
||||
["nsubj:cop", "cop", "amod", "ROOT", "det", "nmod", "punct", "advmod", "appos"],
|
||||
[3, 2, 1, 0, 1, -2, 2, 1, -3],
|
||||
["ala-arvoista käytöstä kaikilta oppilailta", "valvojaoppilailta"],
|
||||
),
|
||||
(
|
||||
"Isä souti veneellä, jonka hän oli vuokrannut",
|
||||
["NOUN", "VERB", "NOUN", "PUNCT", "PRON", "PRON", "AUX", "VERB"],
|
||||
["nsubj", "ROOT", "obl", "punct", "obj", "nsubj", "aux", "acl:relcl"],
|
||||
[1, 0, -1, 4, 3, 2, 1, -5],
|
||||
["Isä", "veneellä"],
|
||||
),
|
||||
(
|
||||
"Kirja, jonka poimin hyllystä, kertoo norsuista",
|
||||
["NOUN", "PUNCT", "PRON", "VERB", "NOUN", "PUNCT", "VERB", "NOUN"],
|
||||
["nsubj", "punct", "obj", "acl:relcl", "obl", "punct", "ROOT", "obl"],
|
||||
[6, 2, 1, -3, -1, 1, 0, -1],
|
||||
["Kirja", "hyllystä", "norsuista"],
|
||||
),
|
||||
(
|
||||
"Huomenna on päivä, jota olemme odottaneet",
|
||||
["NOUN", "AUX", "NOUN", "PUNCT", "PRON", "AUX", "VERB"],
|
||||
["ROOT", "cop", "nsubj:cop", "punct", "obj", "aux", "acl:relcl"],
|
||||
[0, -1, -2, 3, 2, 1, -4],
|
||||
["Huomenna", "päivä"],
|
||||
),
|
||||
(
|
||||
"Liikkuvuuden lisääminen on yksi korkeakoulutuksen keskeisistä kehittämiskohteista",
|
||||
["NOUN", "NOUN", "AUX", "PRON", "NOUN", "ADJ", "NOUN"],
|
||||
["nmod:gobj", "nsubj:cop", "cop", "ROOT", "nmod:poss", "amod", "nmod"],
|
||||
[1, 2, 1, 0, 2, 1, -3],
|
||||
[
|
||||
"Liikkuvuuden lisääminen",
|
||||
"korkeakoulutuksen keskeisistä kehittämiskohteista",
|
||||
],
|
||||
),
|
||||
(
|
||||
"Kaupalliset palvelut jätetään yksityisten palveluntarjoajien tarjottavaksi",
|
||||
["ADJ", "NOUN", "VERB", "ADJ", "NOUN", "NOUN"],
|
||||
["amod", "obj", "ROOT", "amod", "nmod:gsubj", "obl"],
|
||||
[1, 1, 0, 1, 1, -3],
|
||||
["Kaupalliset palvelut", "yksityisten palveluntarjoajien tarjottavaksi"],
|
||||
),
|
||||
(
|
||||
"New York tunnetaan kaupunkina, joka ei koskaan nuku",
|
||||
["PROPN", "PROPN", "VERB", "NOUN", "PUNCT", "PRON", "AUX", "ADV", "VERB"],
|
||||
["obj", "flat:name", "ROOT", "obl", "punct", "nsubj", "aux", "advmod", "acl:relcl"],
|
||||
[2, -1, 0, -1, 4, 3, 2, 1, -5],
|
||||
["New York", "kaupunkina"],
|
||||
),
|
||||
(
|
||||
"Loput vihjeet saat herra Möttöseltä",
|
||||
["NOUN", "NOUN", "VERB", "NOUN", "PROPN"],
|
||||
["compound:nn", "obj", "ROOT", "compound:nn", "obj"],
|
||||
[1, 1, 0, 1, -2],
|
||||
["Loput vihjeet", "herra Möttöseltä"],
|
||||
),
|
||||
(
|
||||
"mahdollisuus tukea muita päivystysyksiköitä",
|
||||
["NOUN", "VERB", "PRON", "NOUN"],
|
||||
["ROOT", "acl", "det", "obj"],
|
||||
[0, -1, 1, -2],
|
||||
["mahdollisuus", "päivystysyksiköitä"],
|
||||
),
|
||||
(
|
||||
"sairaanhoitopiirit harjoittavat leikkaustoimintaa alueellaan useammassa sairaalassa",
|
||||
["NOUN", "VERB", "NOUN", "NOUN", "ADJ", "NOUN"],
|
||||
["nsubj", "ROOT", "obj", "obl", "amod", "obl"],
|
||||
[1, 0, -1, -1, 1, -3],
|
||||
["sairaanhoitopiirit", "leikkaustoimintaa", "alueellaan", "useammassa sairaalassa"],
|
||||
),
|
||||
(
|
||||
"Lain mukaan varhaiskasvatus on suunnitelmallista toimintaa",
|
||||
["NOUN", "ADP", "NOUN", "AUX", "ADJ", "NOUN"],
|
||||
["obl", "case", "nsubj:cop", "cop", "amod", "ROOT"],
|
||||
[5, -1, 3, 2, 1, 0],
|
||||
["Lain", "varhaiskasvatus", "suunnitelmallista toimintaa"],
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
def test_noun_chunks_is_parsed(fi_tokenizer):
|
||||
"""Test that noun_chunks raises Value Error for 'fi' language if Doc is not parsed.
|
||||
To check this test, we're constructing a Doc
|
||||
with a new Vocab here and forcing is_parsed to 'False'
|
||||
to make sure the noun chunks don't run.
|
||||
"""
|
||||
doc = fi_tokenizer("Tämä on testi")
|
||||
with pytest.raises(ValueError):
|
||||
list(doc.noun_chunks)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"text,pos,deps,heads,expected_noun_chunks", FI_NP_TEST_EXAMPLES
|
||||
)
|
||||
def test_fi_noun_chunks(fi_tokenizer, text, pos, deps, heads, expected_noun_chunks):
|
||||
tokens = fi_tokenizer(text)
|
||||
|
||||
assert len(heads) == len(pos)
|
||||
doc = Doc(
|
||||
tokens.vocab,
|
||||
words=[t.text for t in tokens],
|
||||
heads=[head + i for i, head in enumerate(heads)],
|
||||
deps=deps,
|
||||
pos=pos,
|
||||
)
|
||||
|
||||
noun_chunks = list(doc.noun_chunks)
|
||||
assert len(noun_chunks) == len(expected_noun_chunks)
|
||||
for i, np in enumerate(noun_chunks):
|
||||
assert np.text == expected_noun_chunks[i]
|
||||
Loading…
Reference in New Issue
Block a user