A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization

Chenhui Shen, Liying Cheng, Xuan-Phi Nguyen, Yang You, Lidong Bing


Abstract
Pre-trained language models (PLMs) have achieved outstanding achievements in abstractive single-document summarization (SDS). However, such benefits may not fully extend to multi-document summarization (MDS), where the handling of cross-document information is more complex. Previous works either design new MDS architectures or apply PLMs bluntly with concatenated source documents as a reformulated SDS task. While the former does not utilize previous pre-training efforts and may not generalize well across different domains, the latter may not sufficiently attend to the intricate cross-document relationships unique to MDS tasks. Instead, we enforce hierarchy on both the encoder and decoder to better utilize a PLM to facilitate multi-document interactions for the MDS task. Across 10 MDS benchmarks from various domains, our method outperforms or is competitive with the previous best models, including those with additional MDS pre-training or with more parameters. It outperforms its corresponding PLM backbone by up to 3 Rouge-L and is favored by humans.
Anthology ID:
2023.findings-emnlp.391
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5872–5887
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.391
DOI:
10.18653/v1/2023.findings-emnlp.391
Bibkey:
Cite (ACL):
Chenhui Shen, Liying Cheng, Xuan-Phi Nguyen, Yang You, and Lidong Bing. 2023. A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5872–5887, Singapore. Association for Computational Linguistics.
Cite (Informal):
A Hierarchical Encoding-Decoding Scheme for Abstractive Multi-document Summarization (Shen et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.391.pdf