Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization

Dongmin Hyun, Xiting Wang, Chayoung Park, Xing Xie, Hwanjo Yu


Abstract
Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without ground-truth summaries. However, recent unsupervised models are extractive, which remove words from texts and thus they are less flexible than abstractive summarization. In this work, we devise an abstractive model based on reinforcement learning without ground-truth summaries. We formulate the unsupervised summarization based on the Markov decision process with rewards representing the summary quality. To further enhance the summary quality, we develop a multi-summary learning mechanism that generates multiple summaries with varying lengths for a given text, while making the summaries mutually enhance each other. Experimental results show that the proposed model substantially outperforms both abstractive and extractive models, yet frequently generating new words not contained in input texts.
Anthology ID:
2022.findings-emnlp.214
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2939–2951
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.214
DOI:
10.18653/v1/2022.findings-emnlp.214
Bibkey:
Cite (ACL):
Dongmin Hyun, Xiting Wang, Chayoung Park, Xing Xie, and Hwanjo Yu. 2022. Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2939–2951, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization (Hyun et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/2022.findings-emnlp.214.pdf