Research on Entity Recognition Method in Knowledge Base Question Answering

Based on the analysis of the existing knowledge base question answering (KBQA) system, it is found that the open domain KBQA in Chinese lacks support for multi-relational question answering (MRQA). Based on the knowledge base (KB) provided by NLPCC-ICCPOL 2016, MRQA in Chinese domain is explored in this paper. The KBQA process is divided into three steps: entity recognition, entity relation extraction and answer retrieval. Entity recognition is the focus of this paper. A deep leaning model is introduced to identify multiple entities in the question, and the method of similarity calculation is used to link and disambiguate the identified entities with terms in the KB. The experimental results show that the method can support MRQA with a higher average F1 score.