Abstract
We argue that disentangling content selection from the budget used to cover salient content improves the performance and applicability of abstractive summarizers. Our method, FactorSum, does this disentanglement by factorizing summarization into two steps through an energy function: (1) generation of abstractive summary views covering salient information in subsets of the input document (document views); (2) combination of these views into a final summary, following a budget and content guidance. This guidance may come from different sources, including from an advisor model such as BART or BigBird, or in oracle mode – from the reference. This factorization achieves significantly higher ROUGE scores on multiple benchmarks for long document summarization, namely PubMed, arXiv, and GovReport. Most notably, our model is effective for domain adaptation. When trained only on PubMed samples, it achieves a 46.29 ROUGE-1 score on arXiv, outperforming PEGASUS trained in domain by a large margin. Our experimental results indicate that the performance gains are due to more flexible budget adaptation and processing of shorter contexts provided by partial document views.- Anthology ID:
- 2022.emnlp-main.426
- 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:
- 6341–6364
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.426
- DOI:
- 10.18653/v1/2022.emnlp-main.426
- Cite (ACL):
- Marcio Fonseca, Yftah Ziser, and Shay B. Cohen. 2022. Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6341–6364, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents (Fonseca et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.emnlp-main.426.pdf