A REVIEW OF DEEP LEARNING FOR FINDING THE BEST ANSWER IN COMMUNITY QUESTION ANSWERING SYSTEM

Abstract

Answer selection (also called finding the best answer) is a major problem in community question answering system. When a question is posted on the forum, users can answer the question. The purpose of answer selection problem is to sort the answers according to the level of relevance to the question. The best answers will be preceded by less relevant answers. In recent years, many deep learning models have been proposed in many natural language processing problems, including the answer selection. However, these proposed models are performed on different data sets. Therefore, the aim of this paper is to survey and describe thoroughly some deep learning models applying problem of finding the best answer and analyzing some challenges on the data sets for this task in community question answering system.