DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization

Ziming Mao, Chen Henry Wu, Ansong Ni, Yusen Zhang, Rui Zhang, Tao Yu, Budhaditya Deb, Chenguang Zhu, Ahmed Awadallah, Dragomir Radev


Abstract
Transformer-based models have achieved state-of-the-art performance on short-input summarization. However, they still struggle with summarizing longer text. In this paper, we present DYLE, a novel dynamic latent extraction approach for abstractive long-input summarization. DYLE jointly trains an extractor and a generator and treats the extracted text snippets as the latent variable, allowing dynamic snippet-level attention weights during decoding. To provide adequate supervision, we propose simple yet effective heuristics for oracle extraction as well as a consistency loss term, which encourages the extractor to approximate the averaged dynamic weights predicted by the generator. We evaluate our method on different long-document and long-dialogue summarization tasks: GovReport, QMSum, and arXiv. Experiment results show that DYLE outperforms all existing methods on GovReport and QMSum, with gains up to 6.1 ROUGE, while yielding strong results on arXiv. Further analysis shows that the proposed dynamic weights provide interpretability of our generation process.
Anthology ID:
2022.acl-long.118
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1687–1698
Language:
URL:
https://aclanthology.org/2022.acl-long.118
DOI:
10.18653/v1/2022.acl-long.118
Bibkey:
Cite (ACL):
Ziming Mao, Chen Henry Wu, Ansong Ni, Yusen Zhang, Rui Zhang, Tao Yu, Budhaditya Deb, Chenguang Zhu, Ahmed Awadallah, and Dragomir Radev. 2022. DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1687–1698, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization (Mao et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2022.acl-long.118.pdf
Code
 yale-lily/dyle
Data
GovReportQMSum