Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks

TL;DR

This paper introduces a novel heterogeneous graph network that incorporates commonsense knowledge and speaker information to improve abstractive dialogue summarization, demonstrating superior performance on multiple datasets.

Contribution

The paper proposes a Dialogue Heterogeneous Graph Network (D-HGN) that models utterances, commonsense knowledge, and speakers for enhanced dialogue understanding and summarization.

Findings

Outperforms existing methods on SAMSum dataset

Shows better generalization in zero-shot experiments on Argumentative Dialogue Corpus

Effectively models multi-source information for dialogue summarization

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 understanding and summary generation. In detail, we consider utterance and commonsense knowledge 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 Argumentative Dialogue Summary Corpus, the results show that our model can better generalized to the new domain.