def sentence_score_cobalt(self, sentence1, sentence2, alignments, word_level_scores):
functional_words1 = list(filter(lambda x: word_sim.function_word(x.form), sentence1))
functional_words2 = list(filter(lambda x: word_sim.function_word(x.form), sentence2))
weighted_length1 = self.delta * (len(sentence1) - len(functional_words1)) + ((1.0 - self.delta) * len(functional_words1))
weighted_length2 = self.delta * (len(sentence2) - len(functional_words2)) + ((1.0 - self.delta) * len(functional_words2))
weighted_matches1 = 0
weighted_matches2 = 0
for i, a in enumerate(alignments[0]):
if not word_sim.function_word(sentence1[a[0] - 1].form):
weighted_matches1 += self.delta * (max(word_level_scores[i].similarity - word_level_scores[i].penalty_mean, self.minimal_aligned_relatedness))
else:
weighted_matches1 += (1 - self.delta) * (max(word_level_scores[i].similarity - word_level_scores[i].penalty_mean, self.minimal_aligned_relatedness))
if not word_sim.function_word(sentence2[a[1] - 1].form):
weighted_matches2 += self.delta * (max(word_level_scores[i].similarity - word_level_scores[i].penalty_mean, self.minimal_aligned_relatedness))
else:
weighted_matches2 += (1 - self.delta) * (max(word_level_scores[i].similarity - word_level_scores[i].penalty_mean, self.minimal_aligned_relatedness))
if weighted_length1 == 0:
precision = weighted_matches1
else:
precision = weighted_matches1 / weighted_length1
if weighted_length2 == 0:
recall = weighted_matches2
else:
recall = weighted_matches2 / weighted_length2
if precision == 0 or recall == 0 or (((1.0 - self.alpha) / precision) + (self.alpha / recall)) == 0:
fmean = 0
else:
fmean = 1.0 / (((1.0 - self.alpha) / precision) + (self.alpha / recall))
score = fmean
return score
def run(self, cand, ref):
counted = []
aligned_tokens_cand = []
for a in cand['alignments'][0]:
aligned_tokens_cand.append(a[1])
prev = None
for i in sorted(aligned_tokens_cand):
if (prev is None and i > 1) or (prev is not None and (i != prev + 1 and i != prev)):
count = 0
if prev is None:
prev = 0
for j in range(prev, i - prev - 1):
if not word_sim.function_word(ref['tokens'][j]):
count += 1
counted.append(count)
if len(counted) == AbstractChunkFeature.chunk_number:
break
prev = i
if prev is None:
prev = 0
if prev < len(cand['tokens']) and len(counted) < AbstractChunkFeature.chunk_number:
count = 0
for j in range(prev, len(cand['tokens']) - 1):
if not word_sim.function_word(cand['tokens'][j]):
count += 1
counted.append(count)
while len(counted) < AbstractChunkFeature.chunk_number:
counted.append(0)
AbstractChunkFeature.set_value(self, counted)
