explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-04 21:50:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Call morph morphology in GoldParse

Browse Source
This commit is contained in:
Matthew Honnibal 2018-09-25 21:34:53 +02:00
parent 2ba10493f7
commit fb0abddd9e
3 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/cli/ud_train.py
View File

@ -74,7 +74,7 @@ def read_data(nlp, conllu_file, text_file, raw_text=True, oracle_segments=False,
head = int(head)-1 if head != '0' else id_ head = int(head)-1 if head != '0' else id_
sent['words'].append(word) sent['words'].append(word)
sent['tags'].append(tag) sent['tags'].append(tag)
sent['morph'].append(_parse_morph_string(morph)) sent['morphology'].append(_parse_morph_string(morph))
sent['heads'].append(head) sent['heads'].append(head)
sent['deps'].append('ROOT' if dep == 'root' else dep) sent['deps'].append('ROOT' if dep == 'root' else dep)
sent['spaces'].append(space_after == '_') sent['spaces'].append(space_after == '_')

2
spacy/gold.pxd
View File

@ -24,7 +24,7 @@ cdef class GoldParse:
cdef public int loss cdef public int loss
cdef public list words cdef public list words
cdef public list tags cdef public list tags
cdef public list morph cdef public list morphology
cdef public list heads cdef public list heads
cdef public list labels cdef public list labels
cdef public dict orths cdef public dict orths

12
spacy/gold.pyx
View File

@ -399,7 +399,7 @@ cdef class GoldParse:
return cls(doc, words=words, tags=tags, heads=heads, deps=deps, return cls(doc, words=words, tags=tags, heads=heads, deps=deps,
entities=entities, make_projective=make_projective) entities=entities, make_projective=make_projective)
def __init__(self, doc, annot_tuples=None, words=None, tags=None, morph=None, def __init__(self, doc, annot_tuples=None, words=None, tags=None, morphology=None,
heads=None, deps=None, entities=None, make_projective=False, heads=None, deps=None, entities=None, make_projective=False,
cats=None, **_): cats=None, **_):
"""Create a GoldParse. """Create a GoldParse.
@ -436,8 +436,8 @@ cdef class GoldParse:
deps = [None for _ in doc] deps = [None for _ in doc]
if entities is None: if entities is None:
entities = [None for _ in doc] entities = [None for _ in doc]
if morph is None: if morphology is None:
morph = [None for _ in doc] morphology = [None for _ in doc]
elif len(entities) == 0: elif len(entities) == 0:
entities = ['O' for _ in doc] entities = ['O' for _ in doc]
elif not isinstance(entities[0], basestring): elif not isinstance(entities[0], basestring):
@ -462,7 +462,7 @@ cdef class GoldParse:
self.heads = [None] * len(doc) self.heads = [None] * len(doc)
self.labels = [None] * len(doc) self.labels = [None] * len(doc)
self.ner = [None] * len(doc) self.ner = [None] * len(doc)
self.morph = [None] * len(doc) self.morphology = [None] * len(doc)
# This needs to be done before we align the words # This needs to be done before we align the words
if make_projective and heads is not None and deps is not None: if make_projective and heads is not None and deps is not None:
@ -490,12 +490,12 @@ cdef class GoldParse:
self.heads[i] = None self.heads[i] = None
self.labels[i] = None self.labels[i] = None
self.ner[i] = 'O' self.ner[i] = 'O'
self.morph[i] = set() self.morphology[i] = set()
if gold_i is None: if gold_i is None:
if i in i2j_multi: if i in i2j_multi:
self.words[i] = words[i2j_multi[i]] self.words[i] = words[i2j_multi[i]]
self.tags[i] = tags[i2j_multi[i]] self.tags[i] = tags[i2j_multi[i]]
self.morph[i] = morph[i2j_multi[i]] self.morphology[i] = morphology[i2j_multi[i]]
is_last = i2j_multi[i] != i2j_multi.get(i+1) is_last = i2j_multi[i] != i2j_multi.get(i+1)
is_first = i2j_multi[i] != i2j_multi.get(i-1) is_first = i2j_multi[i] != i2j_multi.get(i-1)
# Set next word in multi-token span as head, until last # Set next word in multi-token span as head, until last