A Bag of Tricks for Dialogue Summarization

Muhammad Khalifa, Miguel Ballesteros, Kathleen McKeown


Abstract
Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization. In this work, we explore four different challenges of the task: handling and differentiating parts of the dialogue belonging to multiple speakers, negation understanding, reasoning about the situation, and informal language understanding. Using a pretrained sequence-to-sequence language model, we explore speaker name substitution, negation scope highlighting, multi-task learning with relevant tasks, and pretraining on in-domain data. Our experiments show that our proposed techniques indeed improve summarization performance, outperforming strong baselines.
Anthology ID:
2021.emnlp-main.631
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8014–8022
Language:
URL:
https://aclanthology.org/2021.emnlp-main.631
DOI:
10.18653/v1/2021.emnlp-main.631
Bibkey:
Cite (ACL):
Muhammad Khalifa, Miguel Ballesteros, and Kathleen McKeown. 2021. A Bag of Tricks for Dialogue Summarization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8014–8022, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
A Bag of Tricks for Dialogue Summarization (Khalifa et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2021.emnlp-main.631.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2021.emnlp-main.631.mp4
Data
CommonGenSAMSum