Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks

Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks Xiachong Feng1, Xiaocheng Feng1,2∗, Bing Qin1,2 1Harbin Institute of Technology, China 2Peng Cheng Laboratory, China {xiachongfeng,xcfeng,bqin}@ir.hit.edu.cn Abstract Abstractive dialogue summarization is the task of capturing the highlights of a dialogue and rewriting them into a concise version. In this paper, we present a novel multi-speaker dialogue summarizer to demonstrate how large-scale commonsense knowledge can facilitate dialogue un- derstanding and summary generation. In detail, we consider utterance and commonsense knowl- edge as two different types of data and design a Dialogue Heterogeneous Graph Network (D- HGN) for modeling both information. Meanwhile, we also add speakers as heterogeneous nodes to facilitate information flow. Experimental results on the SAMSum dataset show that our model can outperform various methods. We also conduct zero-shot setting experiments on the Argu- mentative Dialogue Summary Corpus, the results show that our model can better generalized to the new domain. 1 Introduction Automatic summarization is a fundamental task in Natural Language Processing, which aims to con- dense the original input into a shorter version covering salient information and has been continuously studied for decades (Paice, 1990; Kupiec et al., 1999). Recently, online multi-speaker dialogue/meeting has become one of the most important ways for people to communicate with each other in their daily works. Especially due to the spread of COVID-19 worldwide, people are more dependent on online com- munication. In this paper, we focus on dialogue summarization, which can help people quickly grasp the core content of the dialogue without reviewing the complex dialogue context. home my car broke down i have to get to work i really use the help dude can u pick me up Bob where r u? no problem man! i will leave now and be there in like 10min Tom Bob Tom Bob's car has broken down. In 10 minutes Tom will give him a lift to work. give a lift Dialogue Reference Summary Figure 1: An example of dialogue-summary pair. Green for speakers, blue for utterances, and pink for commonsense knowledge. In order to generate “give a lift” in the reference summary, the summarization model needs to understand the commonsense knowledge behind “pick up” and “car broke down”. Recent works that incorporate additional commonsense knowledge in the dialogue generation (Zhou et al., 2018) and dialogue context representation learning (Wang et al., 2020) show that even though neural models have strong learning capabilities, explicit knowledge can still improve response generation quality. It is because that a dialog system can understand conversations better and thus respond more properly if it can access and make full use of large-scale commonsense knowledge. However, current dialogue summarization systems (Ganesh and Dingliwal, 2019; Li et al., 2019; Liu et al., 2019a; Zhu et ∗Corresponding author. ©2021 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License CCL 2021 Proceedings of the 20th China National Conference on Computational Linguistics, pages 964-975, Hohhot, China, Augest 13 - 15, 2021. (c) Technical Committee on Computational Linguistics, Chinese …

Content truncated to 500 words