Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks
This work addresses the problem of generating concise summaries from multi-speaker dialogues for applications like virtual assistants or meeting notes, though it is incremental in combining existing techniques.
The paper tackles abstractive dialogue summarization by incorporating commonsense knowledge via a Dialogue Heterogeneous Graph Network (D-HGN), achieving improved performance on the SAMSum dataset and better generalization in zero-shot experiments on the Argumentative Dialogue Summary Corpus.
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.