Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning

Zhichao Geng, Ming Zhong, Zhangyue Yin, Xipeng Qiu, Xuanjing Huang


Abstract
Pre-trained models have brought remarkable success on the text summarization task. For dialogue summarization, the subdomain of text summarization, utterances are concatenated to flat text before being processed. As a result, existing summarization systems based on pre-trained models are unable to recognize the unique format of the speaker-utterance pair well in the dialogue. To investigate this issue, we conduct probing tests and manual analysis, and find that the powerful pre-trained model can not identify different speakers well in the conversation, which leads to various factual errors. Moreover, we propose three speaker-aware supervised contrastive learning (SCL) tasks: Token-level SCL, Turn-level SCL, and Global-level SCL. Comprehensive experiments demonstrate that our methods achieve significant performance improvement on two mainstream dialogue summarization datasets. According to detailed human evaluations, pre-trained models equipped with SCL tasks effectively generate summaries with better factual consistency.
Anthology ID:
2022.coling-1.569
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6540–6546
Language:
URL:
https://aclanthology.org/2022.coling-1.569
DOI:
Bibkey:
Cite (ACL):
Zhichao Geng, Ming Zhong, Zhangyue Yin, Xipeng Qiu, and Xuanjing Huang. 2022. Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6540–6546, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning (Geng et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.569.pdf
Data
SAMSum Corpus