explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Use merge_mwe=False in evaluation in train.py

Browse Source
This commit is contained in:
Matthew Honnibal 2015-04-08 00:35:19 +02:00
parent cff2b13fef
commit e775e05313
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
bin/parser/train.py
View File

@ -219,7 +219,7 @@ def train(Language, train_loc, model_dir, n_iter=15, feat_set=u'basic', seed=0,
scorer = Scorer() scorer = Scorer()
for raw_text, segmented_text, annot_tuples in gold_tuples: for raw_text, segmented_text, annot_tuples in gold_tuples:
# Eval before train # Eval before train
tokens = nlp(raw_text) tokens = nlp(raw_text, merge_mwes=False)
gold = GoldParse(tokens, annot_tuples) gold = GoldParse(tokens, annot_tuples)
scorer.score(tokens, gold, verbose=False) scorer.score(tokens, gold, verbose=False)
@ -248,7 +248,7 @@ def evaluate(Language, dev_loc, model_dir, gold_preproc=False, verbose=True):
gold_tuples = read_docparse_file(dev_loc) gold_tuples = read_docparse_file(dev_loc)
scorer = Scorer() scorer = Scorer()
for raw_text, segmented_text, annot_tuples in gold_tuples: for raw_text, segmented_text, annot_tuples in gold_tuples:
tokens = nlp(raw_text) tokens = nlp(raw_text, merge_mwes=False)
gold = GoldParse(tokens, annot_tuples) gold = GoldParse(tokens, annot_tuples)
scorer.score(tokens, gold, verbose=verbose) scorer.score(tokens, gold, verbose=verbose)
return scorer return scorer