|
@@ -1919,9 +1919,9 @@ class TendereeRuleRecall():
|
|
|
"(人|公司|单位|组织|用户|业主|主体|方|部门)|文章来源|委托机构|产权所有人|需求?方|买方|业主|(业主|采购人|招标人)联系方式[,:]公司名称:|权属人|甲方当事人|询价书企业|比选发起人|项目单位[,:]单位名称|结算单位)"\
|
|
|
"[))]?(信息[,:])?((公司|单位)?名称)?([((](全称|盖章)[))])?(是|:|:)+)(?P<unrecognized>[^,。::;]+)[,。;::]")
|
|
|
# 未识别实体尾部判断
|
|
|
- self.unrecognized_end1 = re.compile(
|
|
|
- "^[\u4e00-\u9fa5]{2,}?(?:公司|医院|学校|学院|大学|中学|小学|幼儿园|政府|指挥部|办公室|项目部|业主大会|监狱|教育局|委员会|研究所|招标办|采购部|办事处|水利局|公墓|中心|联合社|合作社)")
|
|
|
- self.unrecognized_end2 = re.compile("^[\u4e00-\u9fa5]{4,}(?:署|局|厅|处|室|科|部|站|所|股|行|园)")
|
|
|
+ # self.unrecognized_end1 = re.compile(
|
|
|
+ # "^[\u4e00-\u9fa5]{2,}?(?:公司|医院|学校|学院|大学|中学|小学|幼儿园|政府|指挥部|办公室|项目部|业主大会|监狱|教育局|委员会|研究所|招标办|采购部|办事处|水利局|公墓|中心|联合社|合作社)")
|
|
|
+ # self.unrecognized_end2 = re.compile("^[\u4e00-\u9fa5]{4,}(?:署|局|厅|处|室|科|部|站|所|股|行|园)")
|
|
|
|
|
|
def predict(self, list_articles,list_sentences, list_entitys, list_codenames):
|
|
|
|
|
@@ -1946,10 +1946,10 @@ class TendereeRuleRecall():
|
|
|
self.entity_context_rule(ents,list_name,list_sentences,list(agency_set))
|
|
|
if not self.get_tenderee:
|
|
|
self.subject_rule(ents,list_articles,list_sentences)
|
|
|
- if not self.get_tenderee:
|
|
|
- self.unrecognized_entity_rule(self.unrecognized1,list_sentences,list_entitys,0.55)
|
|
|
- if not self.get_tenderee:
|
|
|
- self.unrecognized_entity_rule(self.unrecognized2,list_sentences,list_entitys,0.5)
|
|
|
+ # if not self.get_tenderee:
|
|
|
+ # self.unrecognized_entity_rule(self.unrecognized1,list_sentences,list_entitys,0.55)
|
|
|
+ # if not self.get_tenderee:
|
|
|
+ # self.unrecognized_entity_rule(self.unrecognized2,list_sentences,list_entitys,0.5)
|
|
|
|
|
|
#entity上下文正则判断
|
|
|
def entity_context_rule(self,entitys,list_name,list_sentences,list_agency):
|