explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-25 03:13:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Skip sentences of length 1 in training

Browse Source
This commit is contained in:
Matthew Honnibal 2015-06-05 02:29:03 +02:00
parent 6bf35cecc3
commit e772b48dcd
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
bin/parser/train.py
View File

@ -178,6 +178,8 @@ def train(Language, gold_tuples, model_dir, n_iter=15, feat_set=u'basic',
else: else:
sents = _merge_sents(sents) sents = _merge_sents(sents)
for annot_tuples, ctnt in sents: for annot_tuples, ctnt in sents:
if len(annot_tuples[1]) == 1:
continue
score_model(scorer, nlp, raw_text, annot_tuples, train_tags) score_model(scorer, nlp, raw_text, annot_tuples, train_tags)
if raw_text is None: if raw_text is None:
tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1]) tokens = nlp.tokenizer.tokens_from_list(annot_tuples[1])