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

Read morphology into gold standard in ud-train

This commit is contained in:
Matthew Honnibal 2018-09-25 21:32:24 +02:00
parent 834dfb0e9d
commit 2ba10493f7
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/cli/ud_train.py
View File

@ -74,6 +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['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 == '_')
@ -101,6 +102,16 @@ def read_data(nlp, conllu_file, text_file, raw_text=True, oracle_segments=False,
return docs, golds return docs, golds
return docs, golds return docs, golds
def _parse_morph_string(morph_string):
if morph_string == '_':
return None
output = []
replacements = {'1': 'one', '2': 'two', '3': 'three'}
for feature in morph_string.split('|'):
key, value = feature.split('=')
value = replacements.get(value, value)
output.append('%s_%s' % (key, value.lower()))
return set(output)
def read_conllu(file_): def read_conllu(file_):
docs = [] docs = []