Incremental temporal summarization in multi-party meetings

Ramesh Manuvinakurike, Saurav Sahay, Wenda Chen, Lama Nachman


Abstract
In this work, we develop a dataset for incremental temporal summarization in a multiparty dialogue. We use crowd-sourcing paradigm with a model-in-loop approach for collecting the summaries and compare the data with the expert summaries. We leverage the question generation paradigm to automatically generate questions from the dialogue, which can be used to validate the user participation and potentially also draw attention of the user towards the contents then need to summarize. We then develop several models for abstractive summary generation in the Incremental temporal scenario. We perform a detailed analysis of the results and show that including the past context into the summary generation yields better summaries.
Anthology ID:
2021.sigdial-1.55
Volume:
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
July
Year:
2021
Address:
Singapore and Online
Editors:
Haizhou Li, Gina-Anne Levow, Zhou Yu, Chitralekha Gupta, Berrak Sisman, Siqi Cai, David Vandyke, Nina Dethlefs, Yan Wu, Junyi Jessy Li
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
530–541
Language:
URL:
https://aclanthology.org/2021.sigdial-1.55
DOI:
10.18653/v1/2021.sigdial-1.55
Bibkey:
Cite (ACL):
Ramesh Manuvinakurike, Saurav Sahay, Wenda Chen, and Lama Nachman. 2021. Incremental temporal summarization in multi-party meetings. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 530–541, Singapore and Online. Association for Computational Linguistics.
Cite (Informal):
Incremental temporal summarization in multi-party meetings (Manuvinakurike et al., SIGDIAL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sigdial-1.55.pdf
Video:
 https://www.youtube.com/watch?v=CnHqotO89jQ
Data
CNN/Daily Mail