Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Ensure root albel is spelled ROOT, for backwards compatibility

This commit is contained in:
Matthew Honnibal 2015-06-23 04:14:03 +02:00
parent 065c2e1d2d
commit 43ef5ddea5
2 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
spacy/gold.pyx
View File

@ -148,6 +148,9 @@ def read_json_file(loc, docs_filter=None):
tags.append(token['tag']) tags.append(token['tag'])
heads.append(token['head'] + i) heads.append(token['head'] + i)
labels.append(token['dep']) labels.append(token['dep'])
# Ensure ROOT label is case-insensitive
if labels[-1].lower() == 'root':
labels[-1] = 'ROOT'
ner.append(token.get('ner', '-')) ner.append(token.get('ner', '-'))
sents.append(( sents.append((
(ids, words, tags, heads, labels, ner), (ids, words, tags, heads, labels, ner),

13
spacy/syntax/arc_eager.pyx
View File

@ -284,12 +284,14 @@ cdef int _get_root(int word, const GoldParseC* gold) nogil:
cdef class ArcEager(TransitionSystem): cdef class ArcEager(TransitionSystem):
@classmethod @classmethod
def get_labels(cls, gold_parses): def get_labels(cls, gold_parses):
move_labels = {SHIFT: {'': True}, REDUCE: {'': True}, RIGHT: {'root': True}, move_labels = {SHIFT: {'': True}, REDUCE: {'': True}, RIGHT: {'ROOT': True},
LEFT: {'root': True}, BREAK: {'root': True}} LEFT: {'ROOT': True}, BREAK: {'ROOT': True}}
for raw_text, sents in gold_parses: for raw_text, sents in gold_parses:
for (ids, words, tags, heads, labels, iob), ctnts in sents: for (ids, words, tags, heads, labels, iob), ctnts in sents:
for child, head, label in zip(ids, heads, labels): for child, head, label in zip(ids, heads, labels):
if label != 'root': if label.upper() == 'ROOT':
label = 'ROOT'
if label != 'ROOT':
if head < child: if head < child:
move_labels[RIGHT][label] = True move_labels[RIGHT][label] = True
elif head > child: elif head > child:
@ -302,8 +304,11 @@ cdef class ArcEager(TransitionSystem):
gold.c.heads[i] = i gold.c.heads[i] = i
gold.c.labels[i] = -1 gold.c.labels[i] = -1
else: else:
label = gold.labels[i]
if label.upper() == 'ROOT':
label = 'ROOT'
gold.c.heads[i] = gold.heads[i] gold.c.heads[i] = gold.heads[i]
gold.c.labels[i] = self.strings[gold.labels[i]] gold.c.labels[i] = self.strings[label]
for end, brackets in gold.brackets.items(): for end, brackets in gold.brackets.items():
for start, label_strs in brackets.items(): for start, label_strs in brackets.items():
gold.c.brackets[start][end] = 1 gold.c.brackets[start][end] = 1