Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks

Feng Xiachong, Feng Xiaocheng, Qin Bing


Abstract
Abstractive dialogue summarization is the task of capturing the highlights of a dialogue andrewriting 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 modelcan 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 tothe new domain.
Anthology ID:
2021.ccl-1.86
Volume:
Proceedings of the 20th Chinese National Conference on Computational Linguistics
Month:
August
Year:
2021
Address:
Huhhot, China
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
964–975
Language:
English
URL:
https://aclanthology.org/2021.ccl-1.86
DOI:
Bibkey:
Cite (ACL):
Feng Xiachong, Feng Xiaocheng, and Qin Bing. 2021. Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks. In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 964–975, Huhhot, China. Chinese Information Processing Society of China.
Cite (Informal):
Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networks (Xiachong et al., CCL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ccl-1.86.pdf