def _align_source_target(self, un_match, un_pos, position, tgt_text,
tgt_pos, align_features):
tgt_dic = {} # list of pairs of words
tgt_word_pos = TMUtilsMatching.segment_2_universal(
tgt_text.lower(), tgt_pos, self.tgt_lang)
for i in range(0, len(tgt_word_pos)):
value_similarity = 0
for f in align_features:
if f == 'word_ter': # TER between words
value_similarity = value_similarity + TMUtilsMatching.ter_distance(
un_match, tgt_word_pos[i][0])
if f == 'posTag': # Boolean PosTag
value_similarity = value_similarity + TMUtilsMatching.pos_bool(
un_pos, tgt_word_pos[i][1])
if f == 'position': # Word position
value_similarity = value_similarity + TMUtilsMatching.position_distance(
position, i)
#if f == 'frequency': # frequency of pairs of words
# value_similarity = value_similarity + self.target_importance(un_word, tgt_word_pos[i][0], segment,best_segments)
# Dictionary have the target word and the position of the word in the target sentence
tgt_dic[(tgt_word_pos[i][0], i)] = value_similarity
tgt_align = sorted(tgt_dic.items(),
key=lambda item: item[1],
reverse=True)[0] # Select the highest score
return tgt_align[0][0], tgt_align[0][
1] # un_word, un_position # Retorn the word with biggest score
def _align_source_target(self, un_match, un_pos, position, tgt_word_pos,
align_features): #tgt_text, tgt_pos,
related_words = []
tgt_dic = {} # list of pairs of words
equal_posTag = [[
position_tgt, word, pos
] for position_tgt, [word, pos] in list(enumerate(tgt_word_pos))
if pos == un_pos.strip(' ') or pos == 'VERB'
or pos == 'NOUN' or pos == 'ADJ']
#print('*************')
#print(equal_posTag)
if not equal_posTag:
return None, None
else:
if 'glossary' in align_features:
related_words = self.search_exact_value(un_match, 10)
for i in range(0, len(equal_posTag)):
value_similarity = 0
for f in align_features:
if f == 'word_ter': # TER between words
value_similarity = value_similarity + (
0.25 * TMUtilsMatching.un_match_distance(
un_match, equal_posTag[i][1]))
if f == 'posTag': # Boolean PosTag
value_similarity = value_similarity + (
0.25 * TMUtilsMatching.pos_bool(
un_pos, equal_posTag[i][2]))
if f == 'position': # Word position
value_similarity = value_similarity + (
0.25 * TMUtilsMatching.position_distance(
position, equal_posTag[i][0]))
if f == 'glossary': # search word on elasticTM
if equal_posTag[i][1] in related_words:
is_related = 1
else:
is_related = 0
value_similarity = value_similarity + (
0.25 * is_related
) #target_importance(un_word, tgt_word_pos[i][0], segment,best_segments)
# Dictionary have the target word and the position of the word in the target sentence --> Low is the best
tgt_dic[(equal_posTag[i][1],
equal_posTag[i][0])] = value_similarity
tgt_align = sorted(tgt_dic.items(),
key=lambda item: item[1],
reverse=True)[0] # Select the highest score
print(
sorted(tgt_dic.items(), key=lambda item: item[1],
reverse=True))
if tgt_align[1] > G_CONFIG.get_src_tgt_threshold():
return tgt_align[0][0], tgt_align[0][1]
else:
return None, None