The Summary Loop: Learning to Write Abstractive Summaries Without Examples

Philippe Laban, Andrew Hsi, John Canny, Marti A. Hearst


Abstract
This work presents a new approach to unsupervised abstractive summarization based on maximizing a combination of coverage and fluency for a given length constraint. It introduces a novel method that encourages the inclusion of key terms from the original document into the summary: key terms are masked out of the original document and must be filled in by a coverage model using the current generated summary. A novel unsupervised training procedure leverages this coverage model along with a fluency model to generate and score summaries. When tested on popular news summarization datasets, the method outperforms previous unsupervised methods by more than 2 R-1 points, and approaches results of competitive supervised methods. Our model attains higher levels of abstraction with copied passages roughly two times shorter than prior work, and learns to compress and merge sentences without supervision.
Anthology ID:
2020.acl-main.460
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5135–5150
Language:
URL:
https://aclanthology.org/2020.acl-main.460
DOI:
10.18653/v1/2020.acl-main.460
Bibkey:
Cite (ACL):
Philippe Laban, Andrew Hsi, John Canny, and Marti A. Hearst. 2020. The Summary Loop: Learning to Write Abstractive Summaries Without Examples. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5135–5150, Online. Association for Computational Linguistics.
Cite (Informal):
The Summary Loop: Learning to Write Abstractive Summaries Without Examples (Laban et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.acl-main.460.pdf
Video:
 http://slideslive.com/38929183
Code
 cannylab/summary_loop
Data
CNN/Daily MailNEWSROOM