Open Domain Question Answering based on Text Enhanced Knowledge Graph with Hyperedge Infusion

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1475–1481 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 1475 Open Domain Question Answering based on Text Enhanced Knowledge Graph with Hyperedge Infusion Jiale Han, Bo Cheng, Xu Wang State Key Laboratory of networking and switching technology, Beijing University of Posts and Telecommunications {hanjl,chengbo,wxx}@bupt.edu.cn Abstract The incompleteness of knowledge base (KB) is a vital factor limiting the performance of question answering (QA). This paper proposes a novel QA method by leveraging text informa- tion to enhance the incomplete KB. The model enriches the entity representation through se- mantic information contained in the text, and employs graph convolutional networks to up- date the entity status. Furthermore, to exploit the latent structural information of text, we treat the text as hyperedges connecting enti- ties among it to complement the deficient re- lations in KB, and hypergraph convolutional networks are further applied to reason on the hypergraph-formed text. Extensive ex- periments on the WebQuestionsSP benchmark with different KB settings prove the effective- ness of our model. 1 Introduction Open domain question answering (QA) is a chal- lenging task that requires answering the factual questions in natural language. According to the structure of supporting information, QA system can be divided into knowledge-based QA (KBQA) (Bordes et al., 2015; Zhang et al., 2018) and text- based QA (TBQA) (Welbl et al., 2018; Yang et al., 2018). KBQA obtains the answers by a structured knowledge base, which is easy to query and reason with but limited by the incompleteness of well- designed triples. TBQA’s supporting information is plain text containing rich semantic and latent structural information, however, it’s difficult for a machine to understand. The complementary prop- erties inspire us to fuse these two kinds of data to enhance the incomplete KB and further improve the QA system’s performance. Some work has already been proposed. Das et al. (2017) represent KB and text using universal schema and apply memory networks, but lack the master's degree writer degreeCleary major gender profession Library Science female writer Cleary master's degree degree major gender profession Scien Question: Which university did Cleary graduate from? writer Cleary master's degree degree major gender profession Library Science University of Washington female master's degree writer Cleary degree major gender profession Library Science female Text: Cleary obtained her master's degree in Library Science at the University of Washington. Figure 1: Example of a question with its related KB and text. The KB is incomplete to answer the question, which lacks relation ”graduated university” and entity ”University of Washington”. By completing the miss- ing information with adding text as hyperedge, we can handle the question more effectively. association between KB and text. Sun et al. (2018) build a heterogeneous graph with entities and text as nodes and employ a graph based method. Xiong et al. (2019) first encode entities in KB by graph at- tention networks and then read text with the help of accumulated entity knowledge. Although good re- sults have been achieved, the …

Content truncated to 500 words