explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-14 13:47:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Hack in WSD scoring

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-03 09:25:52 +02:00
parent 68f174b235
commit b977d60bf4
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/scorer.py
View File

@ -40,6 +40,7 @@ class Scorer(object):
self.labelled = PRFScore() self.labelled = PRFScore()
self.tags = PRFScore() self.tags = PRFScore()
self.ner = PRFScore() self.ner = PRFScore()
self.wsd = PRFScore()
self.eval_punct = eval_punct self.eval_punct = eval_punct
@property @property
@ -73,7 +74,7 @@ class Scorer(object):
def score(self, tokens, gold, verbose=False): def score(self, tokens, gold, verbose=False):
assert len(tokens) == len(gold) assert len(tokens) == len(gold)
#self._score_senses(tokens, gold) self._score_senses(tokens, gold)
gold_deps = set() gold_deps = set()
gold_tags = set() gold_tags = set()
@ -129,7 +130,9 @@ class Scorer(object):
def _score_senses(self, tokens, gold): def _score_senses(self, tokens, gold):
for i, g_annot in enumerate(gold.orig_annot): for i, g_annot in enumerate(gold.orig_annot):
gold_senses = g_annot[-1] gold_senses = g_annot[-1]
if gold_senses: if gold_senses and gold.gold_to_cand[i] is not None:
cand_i = gold.gold_to_cand[i] cand_i = gold.gold_to_cand[i]
sense_str = tokens[cand_i].sense_ sense_str = tokens[cand_i].sense_
print sense_str, gold_senses sense_str = sense_str.replace('N_', 'noun.').replace('V_', 'verb.')
self.wsd.tp += sense_str in gold_senses
self.wsd.fn += sense_str not in gold_senses