def getCandidateSet(EtoV_sent, VtoE_sent, sent_index):
'''
Get Candidate Set of 1 sentence pair
'''
EtoV_set = EtoV_model.getEntSetFromFile(EtoV_sent['Source'],
EtoV_sent['Target'], sent_index)
VtoE_set = VtoE_model.getEntSetFromFile(VtoE_sent['Source'],
VtoE_sent['Target'], sent_index)
V_Ent_List = []
E_Ent_List = []
for pair in EtoV_set:
V_Ent_List.append((pair[1], pair[2], pair[4]))
E_Ent_List.append((pair[0], pair[2], pair[3]))
for pair in VtoE_set:
E_Ent_List.append((pair[1], pair[2], pair[4]))
V_Ent_List.append((pair[0], pair[2], pair[3]))
res = []
for en_ent in E_Ent_List:
for vn_ent in V_Ent_List:
res.append((en_ent[0], vn_ent[0], en_ent[1], en_ent[2], vn_ent[2],
vn_ent[1]))
res = utilities.make_unique(res)
return res
def getNEPair(EtoV_sent,
VtoE_sent,
list_lambda,
sent_index,
mode,
train_mode_InSens=False,
train_mode_Sens=False):
'''
Input: EtoV_sent, VtoE_sent
Output: NE Pairs List of a sentence pair
'''
res = []
if train_mode_InSens or train_mode_Sens:
CandidateSet = getCandidateSet.getCandidateSetFromFile(
sent_index, mode)
else:
CandidateSet = getCandidateSet.getCandidateSet(EtoV_sent, VtoE_sent,
sent_index)
CombineScore = {}
CombineScore['TypeSens'] = getCombineScore_TypeSens.getCombineScore(
CandidateSet,
EtoV_sent,
VtoE_sent,
list_lambda,
sent_index,
mode,
train_mode=train_mode_Sens)
CombineScore['TypeInSens'] = getCombineScore_InSens.getCombineScore(
CandidateSet,
EtoV_sent,
VtoE_sent,
list_lambda,
sent_index,
train_mode=train_mode_InSens)
# print('CombineScore TypeSens', CombineScore['TypeSens'])
res = getFinalRes.getFinalNEPair(CombineScore, CandidateSet, sent_index)
res = utilities.make_unique(res)
# print('After Reassign', res)
return res
def evaluateSentencePair(predict,true_set):
'''
Compare predict set and true set of a sentence pair
'''
tp = 0
predict = utilities.make_unique(predict)
predict = sorted(predict, key=lambda tmp: tmp[0])
# print(predict)
# print('Predict Set ', predict)
# print('True Set ', true_set)
for i in range(len(true_set)):
true_en_begin = true_set[i][0][0]
# print('True_en_begin ',true_en_begin)
true_en_end = true_set[i][0][-1]
# print('True_en_end ',true_en_end)
sub_predict = []
for j in range(len(predict)):
if len(predict[j][0]) < 1:
continue
predict_en_begin = predict[j][0][0]
# print('PredictEnBegin ', predict_en_begin)
if predict_en_begin == true_en_begin:
sub_predict.append(predict[j])
# print('SubPredict ',sub_predict)
if(len(sub_predict)) > 0:
for pair in sub_predict:
# print(pair)
predict_en_end = pair[0][-1]
if predict_en_end == true_en_end:
if len(pair[1]) < 1:
continue
predict_vi_begin = pair[1][0]
predict_vi_end = pair[1][-1]
true_vi_begin = true_set[i][1][0]
true_vi_end = true_set[i][1][-1]
if true_vi_begin == predict_vi_begin and true_vi_end == predict_vi_end:
tp += 1
# print('TP ', tp)
return tp
def evaluateSentencePair(predict, true_set, mode):
'''
Compare predict set and true set of a sentence pair
'''
print('==================')
tp = 0
predict = utilities.make_unique(predict)
# print('evaluateSentencePair',predict)
predict = sorted(predict, key=lambda tmp: tmp[0])
# print('Predict Set', predict)
# print(predict)
# print('Predict Set ', predict)
# print('True Set ', true_set)
for i in range(len(true_set)):
true_en_begin = true_set[i][0][0]
# print('True_en_begin ',true_en_begin)
true_en_end = true_set[i][0][-1]
# print('True_en_end ',true_en_end)
sub_predict = []
for j in range(len(predict)):
if len(predict[j][0]) < 1:
continue
predict_en_begin = predict[j][0][0]
# print('PredictEnBegin ', predict_en_begin)
if predict_en_begin == true_en_begin:
sub_predict.append(predict[j])
# print('SubPredict ',sub_predict)
if (len(sub_predict)) > 0:
for pair in sub_predict:
# print(pair)
predict_en_end = pair[0][-1]
if predict_en_end == true_en_end:
if len(pair[1]) < 1:
continue
# print('Predict Pair',pair)
predict_vi_begin = pair[1][0]
predict_vi_end = pair[1][-1]
true_vi_begin = true_set[i][1][0]
true_vi_end = true_set[i][1][-1]
if true_vi_begin == predict_vi_begin and true_vi_end == predict_vi_end:
tp += 1
else:
candidateset = CandidateSet.getCandidateSetFromFile(
pair[-2], mode)
# print('CandidateSet', candidateset)
for k in range(len(candidateset)):
print('#####################')
print('Candidate', candidateset[k])
print(
'Score',
ScoreTable.getScoreforOneCandidate_TypeInSens(
pair[-2], k))
print('--------------')
print('True', true_set[i])
print('Predict', pair)
print(
'Score',
ScoreTable.getScoreforOneCandidate_TypeInSens(
pair[-2], pair[-1]))
print('Spacy Vi',
VtoE_model.getEntList_Spacy_FromFile(pair[-2]))
print('Spacy En',
EtoV_model.getEntList_Spacy_FromFile(pair[-2]))
print(
'Stanford En',
EtoV_model.getEntList_StanfordNER_FromFile(
pair[-2]))
print(
'Stanford Vi',
VtoE_model.getEntList_StanfordNER_FromFile(
pair[-2]))
# print('TP ', tp)
return tp