sporada/nlp
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp.git synced 2025-07-01 15:20:36 +00:00
Code Issues Projects Releases Wiki Activity

Fix long text processing

Browse Source
This commit is contained in:
Patrick Jentsch
2021-04-22 08:43:34 +02:00
parent cd976692d6
commit 2813d1a222
2 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
spacy-nlp
View File

@ -142,12 +142,12 @@ for text_chunk in text_chunks:
for ent_candidate in token.sent.ents:
if ent_candidate.start_char == token.idx:
ent = ent_candidate
annotation = {'start': ent.start_char + chunk_offset,
'end': ent.end_char + chunk_offset,
'tag': 'ent',
'properties': {'type': token.ent_type_}}
annotations.append(annotation)
break
annotation = {'start': ent.start_char + chunk_offset,
'end': ent.end_char + chunk_offset,
'tag': 'ent',
'properties': {'type': token.ent_type_}}
annotations.append(annotation)
annotation = {'start': token.idx + chunk_offset,
'end': token.idx + len(token.text) + chunk_offset,
'tag': 'token',
@ -157,7 +157,7 @@ for text_chunk in text_chunks:
if token.ent_type_:
annotation['properties']['ner'] = token.ent_type_
annotations.append(annotation)
chunk_offset = len(text_chunk)
chunk_offset += len(text_chunk)
with open(args.output, 'w') as output_file:
json.dump({'meta': meta, 'tags': tags, 'annotations': annotations},