Self-Supervised and Controlled Multi-Document Opinion Summarization

Hady Elsahar, Maximin Coavoux, Jos Rozen, Matthias Gallé


Abstract
We address the problem of unsupervised abstractive summarization of collections of user generated reviews through self-supervision and control. We propose a self-supervised setup that considers an individual document as a target summary for a set of similar documents. This setting makes training simpler than previous approaches by relying only on standard log-likelihood loss and mainstream models. We address the problem of hallucinations through the use of control codes, to steer the generation towards more coherent and relevant summaries.
Anthology ID:
2021.eacl-main.141
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1646–1662
Language:
URL:
https://aclanthology.org/2021.eacl-main.141
DOI:
10.18653/v1/2021.eacl-main.141
Bibkey:
Cite (ACL):
Hady Elsahar, Maximin Coavoux, Jos Rozen, and Matthias Gallé. 2021. Self-Supervised and Controlled Multi-Document Opinion Summarization. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1646–1662, Online. Association for Computational Linguistics.
Cite (Informal):
Self-Supervised and Controlled Multi-Document Opinion Summarization (Elsahar et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.141.pdf