Nothing Special   »   [go: up one dir, main page]

Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization

Junpeng Liu, Yanyan Zou, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Caixia Yuan, Xiaojie Wang


Abstract
Unlike well-structured text, such as news reports and encyclopedia articles, dialogue content often comes from two or more interlocutors, exchanging information with each other. In such a scenario, the topic of a conversation can vary upon progression and the key information for a certain topic is often scattered across multiple utterances of different speakers, which poses challenges to abstractly summarize dialogues. To capture the various topic information of a conversation and outline salient facts for the captured topics, this work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task. The proposed contrastive objectives are framed as auxiliary tasks for the primary dialogue summarization task, united via an alternative parameter updating strategy. Extensive experiments on benchmark datasets demonstrate that the proposed simple method significantly outperforms strong baselines and achieves new state-of-the-art performance. The code and trained models are publicly available via .
Anthology ID:
2021.findings-emnlp.106
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1229–1243
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.106
DOI:
10.18653/v1/2021.findings-emnlp.106
Bibkey:
Cite (ACL):
Junpeng Liu, Yanyan Zou, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Caixia Yuan, and Xiaojie Wang. 2021. Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1229–1243, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization (Liu et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.106.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.106.mp4
Code
 junpliu/condigsum
Data
SAMSum