汉语嵌套命名实体识别方法分析-模式识别与智能系统专业论文.docxVIP

—IF———些丝丝一㈣螋 —IF———些丝丝一㈣螋—iiii萱宣iiiiiiii萱iiiiii置iiiiiiiiiiiiiiiiiiiii宣iiiiiiii宣宣萱一 Ⅲ川叫川川圳洲Ⅲ川I洲洲川川川 Abstra ct With the rapid development of the internet,the expansion of information in networks forms the unprecedented‘‘Big Bang’．The extraction of necessary information and knowledge from large-scale and unstructured text has become a research focus as well as a challenge in natural language processing．As one of the important sub-tazks of information extraction，named entity recognition(NER)aims to identify phrases within sentences and documents that express person names，location names，organization names，data and time，and numeral expressions．Named entity recognition plays a key role in many natural language processing applications such as information retrieval， question answering and machine translation． The thesis introduce entity morphemes into Chinese HER,and thus incorporates entity-internal structural features、7l，itll contextual information under the framework of machine learning to identify person names，location names and organization names in Chinese texts，especially nested location names and organization names． First,four two-layer models ale constructed for Chinese NER based on maximum entropy and conditional random fields(CRFs)．The contrastive experiments on different data sets showed that the CRF··based two·-layer model is much more appropriate for Chinese nested NER．Moreover,a post-processing method based on mutual information is to leVise some possible errors yielded by the CRF—layer model．Our experiments showed that the nested NER performance can be ftLrther improved usmg the post-processing module． Second，simple named entity recognition and nested NER arc considered as two separate tasks in the present study．As such，a five-layer sequence labeling scheme is ————一 ——·一proposed to handle lexical features and phrase SUUeUIre under。the CRF-layer model+to。一——’。。—。 一 flHther enhance nested named entities recognition． Finally,entity morphemes are introduced i