RefSum: Refactoring Neural Summarization

Yixin Liu, Zi-Yi Dou, Pengfei Liu


Abstract
Although some recent works show potential complementarity among different state-of-the-art systems, few works try to investigate this problem in text summarization. Researchers in other areas commonly refer to the techniques of reranking or stacking to approach this problem. In this work, we highlight several limitations of previous methods, which motivates us to present a new framework Refactor that provides a unified view of text summarization and summaries combination. Experimentally, we perform a comprehensive evaluation that involves twenty-two base systems, four datasets, and three different application scenarios. Besides new state-of-the-art results on CNN/DailyMail dataset (46.18 ROUGE-1), we also elaborate on how our proposed method addresses the limitations of the traditional methods and the effectiveness of the Refactor model sheds light on insight for performance improvement. Our system can be directly used by other researchers as an off-the-shelf tool to achieve further performance improvements. We open-source all the code and provide a convenient interface to use it: https://github.com/yixinL7/Refactoring-Summarization.
Anthology ID:
2021.naacl-main.113
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1437–1448
Language:
URL:
https://aclanthology.org/2021.naacl-main.113
DOI:
10.18653/v1/2021.naacl-main.113
Bibkey:
Cite (ACL):
Yixin Liu, Zi-Yi Dou, and Pengfei Liu. 2021. RefSum: Refactoring Neural Summarization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1437–1448, Online. Association for Computational Linguistics.
Cite (Informal):
RefSum: Refactoring Neural Summarization (Liu et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2021.naacl-main.113.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-1/2021.naacl-main.113.mp4
Code
 yixinL7/Refactoring-Summarization
Data
CNN/Daily MailWikiHow