Q-learning with Language Model for Edit-based Unsupervised Summarization

Ryosuke Kohita, Akifumi Wachi, Yang Zhao, Ryuki Tachibana


Abstract
Unsupervised methods are promising for abstractive textsummarization in that the parallel corpora is not required. However, their performance is still far from being satisfied, therefore research on promising solutions is on-going. In this paper, we propose a new approach based on Q-learning with an edit-based summarization. The method combines two key modules to form an Editorial Agent and Language Model converter (EALM). The agent predicts edit actions (e.t., delete, keep, and replace), and then the LM converter deterministically generates a summary on the basis of the action signals. Q-learning is leveraged to train the agent to produce proper edit actions. Experimental results show that EALM delivered competitive performance compared with the previous encoder-decoder-based methods, even with truly zero paired data (i.e., no validation set). Defining the task as Q-learning enables us not only to develop a competitive method but also to make the latest techniques in reinforcement learning available for unsupervised summarization. We also conduct qualitative analysis, providing insights into future study on unsupervised summarizers.
Anthology ID:
2020.emnlp-main.34
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
470–484
Language:
URL:
https://aclanthology.org/2020.emnlp-main.34
DOI:
10.18653/v1/2020.emnlp-main.34
Bibkey:
Cite (ACL):
Ryosuke Kohita, Akifumi Wachi, Yang Zhao, and Ryuki Tachibana. 2020. Q-learning with Language Model for Edit-based Unsupervised Summarization. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 470–484, Online. Association for Computational Linguistics.
Cite (Informal):
Q-learning with Language Model for Edit-based Unsupervised Summarization (Kohita et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.34.pdf
Video:
 https://slideslive.com/38938716
Code
 kohilin/ealm