Graph-Based Knowledge Integration for Question Answering over Dialogue

Proceedings of the 28th International Conference on Computational Linguistics, pages 2425–2435 Barcelona, Spain (Online), December 8-13, 2020 2425 Graph-Based Knowledge Integration for Question Answering over Dialogue Jian Liu1,2,3∗, Dianbo Sui1,2∗, Kang Liu1,2, Jun Zhao1,2 1 National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, 100190, China 2 University of Chinese Academy of Sciences 3 Beijing Jiaotong University, 100044, China jianliu@bjtu.edu.cn; {dianbo.sui, kliu, jzhao}@nlpr.ia.ac.cn Abstract Question answering over dialogue, a specialized machine reading comprehension task, aims to comprehend a dialogue and to answer specific questions. Despite many advances, existing ap- proaches for this task did not consider dialogue structure and background knowledge (e.g., rela- tionships between speakers). In this paper, we introduce a new approach for the task, featured by its novelty in structuring dialogue and integrating background knowledge for reasoning. Specif- ically, different from previous “structure-less” approaches, our method organizes a dialogue as a “relational graph”, using edges to represent relationships between entities. To encode this re- lational graph, we devise a relational graph convolutional network (R-GCN), which can traverse the graph’s topological structure and effectively encode multi-relational knowledge for reason- ing. The extensive experiments have justified the effectiveness of our approach over competitive baselines. Moreover, a deeper analysis shows that our model is better at tackling complex ques- tions requiring relational reasoning and defending adversarial attacks with distracting sentences. 1 Introduction Humans obtain information by engaging in conversations. Question answering (QA) over dialogue, a specialized machine reading comprehension (MRC) task (Hermann et al., 2015), aims to test the ability of a QA system to comprehend a dialogue, by asking it to answer questions about the dialogue. Consider the example shown in Table 1. Given a dialogue and a related question Q1: “What is Joey going to do with Kathy tonight?”, the task requires a system to give the correct answer “having a late dinner”. U1 Chandler: Hey-Hey-Hey! Who was that? U2 Joey: That would be Casey. We’re going out :::::: tonight. U3 Chandler: Goin’ out, huh? Wow! Wow! So things didn’t work out with Kathy, huh? Bummer. U4 Joey: No. Things are fine with Kathy. [I’m having a late dinner with her :::::: tonight], right after my early dinner with Casey. Q1 What is Joey going to do with Kathy tonight? A1 having a late dinner Q2 ::::: When will Joey have dinner with Casey? A2 :::::: tonight Table 1: Up: a dialogue from FriendsQA corpus (Yang and Choi, 2019). Down: two related questions with their answers. An evidence sentence for inferring A1 is given in []. Compared with other MRC tasks, QA over dialogue is more challenging (Yang and Choi, 2019) owing to that conversations often involve complex relationships and background knowledge. In detail, studies show that a dialogue with 12 turns contains 6.1 co-reference chains (Zhou and Choi, 2018) and expresses 4.5 relationships (Yu et al., 2020) on the average. Therefore, to excel in this task, a QA system must master background knowledge for reasoning. Let us consider the reasoning process of Q1 …

Content truncated to 500 words