BamnetTL: Bidirectional Attention Memory Network with Transfer Learning for Question Answering Matching

Abstract

In KBQA (knowledge base question answering), questions are processed using NLP (natural language processing), and knowledge base technology is used to generate the corresponding answers. KBQA is one of the most challenging tasks in the field of NLP. Q&A (question and answer) matching is an important part of knowledge base QA (question answering), in which the correct answer is selected from candidate answers. At present, Q&A matching task faces the problem of lacking training data in new fields, which leads to poor performance and low efficiency of the question answering system. The paper puts forward a KBQA Q&A matching model for deep feature transfer based on a bidirectional attention memory network, BamnetTL. It uses biattention to collect information from the knowledge base and question sentences in both directions in order to improve the accuracy of Q&A matching and transfers knowledge from different fields through a deep dynamic adaptation network. BamnetTL improves the accuracy of Q&A matching in the target domain by transferring the knowledge in the source domain with more training resources to the target domain with fewer training resources. The experimental results show that the proposed method is effective.