Towards Summary Candidates Fusion

Mathieu Ravaut, Shafiq Joty, Nancy Chen


Abstract
Sequence-to-sequence deep neural models fine-tuned for abstractive summarization can achieve great performance on datasets with enough human annotations. Yet, it has been shown that they have not reached their full potential, with a wide gap between the top beam search output and the oracle beam. Recently, re-ranking methods have been proposed, to learn to select a better summary candidate. However, such methods are limited by the summary quality aspects captured by the first-stage candidates. To bypass this limitation, we propose a new paradigm in second-stage abstractive summarization called SummaFusion that fuses several summary candidates to produce a novel abstractive second-stage summary. Our method works well on several summarization datasets, improving both the ROUGE scores and qualitative properties of fused summaries. It is especially good when the candidates to fuse are worse, such as in the few-shot setup where we set a new state-of-the art. We will make our code and checkpoints available at https://github.com/ntunlp/SummaFusion/.
Anthology ID:
2022.emnlp-main.581
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8488–8504
Language:
URL:
https://aclanthology.org/2022.emnlp-main.581
DOI:
10.18653/v1/2022.emnlp-main.581
Bibkey:
Cite (ACL):
Mathieu Ravaut, Shafiq Joty, and Nancy Chen. 2022. Towards Summary Candidates Fusion. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8488–8504, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Towards Summary Candidates Fusion (Ravaut et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.581.pdf