Recognition Method of Feature Word Terms in Chinese Named Entities

Abstract

Natural language processing is an important issue in the field of computer science and artificial intelligence. Compared with English, Chinese lacks explicit markup, and is more flexible in terms of grammar, semantics, and pragmatics, which increases the difficulty of computer understanding and processing. A named entity (NE) refers to an entity with a specific meaning in the text. It mainly includes a person’s name, a place name, an institution name, and a proper noun. Named entity recognition is an important basis for information extraction, automatic question answering, and machine translation. This article provides a method for identifying feature word terms in Chinese named entities. Identifying the correct feature word terms from the named entities is beneficial to effectively correct the segmentation results, improve the accuracy of the segmentation, and the correctness of unregistered word recognition. It is helpful for the analysis of keyword query and natural language query in information retrieval.