def entityRecognize(word_list, question):
entity_list = []
for word in word_list:
entity = ""
finalentity = ""
for temp_entity in word_list[word_list.index(word):]:
entity = entity + temp_entity
all_entity = [entity]
if len(entity) > 1:
# print(entity)
# print(1)
if entity in mention2entity_dic: # 如果它有对应的实体
for alias in mention2entity_dic[entity]:
all_entity.append(alias)
for en in all_entity:
same_name_entity_list = ccksNeo.get_entity_list_by_name(en)
extra_name = ccksNeo.get_entity_info_by_name(en)
for name in extra_name:
if name[0][-1] == '名' or name[0][-1] == '称':
if len(name[1]) > 1:
if name[0] != '英文名' and name[0] != '英文名称' and name[0] != '外文名' and name[0] != '外文名称':
entity_list.append(name[1])
if len(same_name_entity_list) >= 1:
entity_list.append(en)
# print(list(set(entity_list)))
for entity1 in entity_list: # 如果短的指称被长的指称包含，检测短指称的一度关系名
temp = question
for i in entity1:
if i in question:
temp = temp.replace(i, "")
# temp_list = sentence.replace(entity1, "")
# segmentor1 = Segmentor()
# segmentor1.load("./ltpdata/ltp_data_v3.4.0/cws.model")
# temp_list = segmentor1.segment(temp)
# segmentor1.release()
for entity2 in entity_list:
if entity1 != entity2 and entity1 in entity2:
# print(2)
same_name_entity_list = ccksNeo.get_entity_list_by_name(entity1)
flag = 0
for entitydict in same_name_entity_list:
# print(entitydict, "用id查")
# print(3)
relations = ccksNeo.get_related_entities_by_id(entitydict['id'])
# print(relations)
for relation in relations: # 除掉实体的剩余句子
score = serviceWord2vec.get_similarity(list(jieba.cut(temp)), list(jieba.cut(relation['name'])))
if score > 0.2:
flag = 1
if flag == 0 and entity1 in entity_list:
# print(entity_list)
# print(entity1)
entity_list.remove(entity1)
print("entity_list", entity_list)
# time.sleep(10)
return entity_list
yitiaodaan = []
index2 = line.find('|||||')
try:
yitiao = line.split("|||||")[1]
except:
print(1)
try:
yitiaodaan = yitiao.split("||")
except:
print(3)
an21 = []
if yitiaodaan:
for i in yitiaodaan:
if i != ' ':
try:
an21.append(i.split("|")[2])
except:
print(1)
comp = list(set(an21))
for mm in comp:
info = ccksNeo.get_entity_info_by_name(mm)
if info != []:
sentence = sentence + '\t' + '<' + mm + '>'
else:
sentence = sentence + '\t' + '“' + mm + '”'
print(comp)
p.writelines(sentence + '\n')
