Improving Query Graph Generation for Complex Question Answering over Knowledge Base

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4201–4207 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 4201 Improving Query Graph Generation for Complex Question Answering over Knowledge Base Kechen Qin1 Cheng Li2 Virgil Pavlu1 Javed A. Aslam1 1Khoury College of Computer Sciences, Northeastern University 2 CodaMetrix 1qin.ke@northeastern.edu {vip,jaa}@ccs.neu.edu 2cheng@codametrix.com Abstract Most of the existing Knowledge-based Ques- tion Answering (KBQA) methods first learn to map the given question to a query graph, and then convert the graph to an executable query to find the answer. The query graph is typ- ically expanded progressively from the topic entity based on a sequence prediction model. In this paper, we propose a new solution to query graph generation that works in the op- posite manner: we start with the entire knowl- edge base and gradually shrink it to the desired query graph. This approach improves both the efficiency and the accuracy of query graph generation, especially for complex multi-hop questions. Experimental results show that our method achieves state-of-the-art performance on ComplexWebQuestion (CWQ) dataset. 1 Introduction Knowledge-based question answering (KBQA) is the task of finding answers to questions by process- ing a structured knowledge base KB. A KB graph consists of general facts which are organized as entity-relation-entity triplets, with entities as ver- tices and relations as edges. To answer a simple question such as: “Who is the president of the United States?”, a typical KBQA system first iden- tifies the entity (i.e., “United States”) and the rela- tion (i.e., “president”) asked in the question, and then searches for the answer entity by matching the triplet fact query <United States, president, ?> over KB (Bordes et al., 2015; Yin et al., 2016; Yu et al., 2017; Zhang et al., 2018; Zhao et al., 2019). To answer a multi-hop question, multiple facts are ex- tracted to form a structured representation, namely, a query graph (Yih et al., 2015). For example, the question “What was the name of the publisher for Disney Channel Magazine’s first cartoon?” cor- responds to a query graph that consists of 3 facts with grounded (i.e., topic entity) and ungrounded entities (i.e., “?”): <?, publisher, Disney Channel Magazine>, <?, cartoon, ?>, <?, published date, ?>, and a constraint: order by. The query graph can be converted to an executable query to find the an- swer in KB. Generating the query graph accurately and efficiently is the key challenge in KBQA. While single-hop questions are easy to answer by searching for a single fact in KB, multi-hop questions are much harder to answer because the search space grows exponentially as the number of hops increases. The most common way to solve a multi-hop question is to first generate candidate query graphs and then validate and rank them down to one. Previous works construct candidate query graphs by starting with the topic entity and progres- sively expanding the graph (Bao et al., 2016; Liang et al., 2017; Zhou et al., 2018; Luo et al., 2018; Chen et al., 2019). …

Content truncated to 500 words