Abstract
A modular approach has the advantage of being compositional and controllable, comparing to most end-to-end models. In this paper we propose Extract-Select-Rewrite (ESR), a three-phase abstractive sentence summarization method. We decompose summarization into three stages: (i) knowledge extraction, where we extract relation triples from the text using off-the-shelf tools; (ii) content selection, where a subset of triples are selected; and (iii) rewriting, where the selected triple are realized into natural language. Our results demonstrates that ESR is competitive with the best end-to-end models while being more faithful. %than these baseline models. Being modular, ESR’s modules can be trained on separate data which is beneficial in low-resource settings and enhancing the style controllability on text generation.- Anthology ID:
- 2023.newsum-1.4
- Volume:
- Proceedings of the 4th New Frontiers in Summarization Workshop
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Yue Dong, Wen Xiao, Lu Wang, Fei Liu, Giuseppe Carenini
- Venue:
- NewSum
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 41–48
- Language:
- URL:
- https://aclanthology.org/2023.newsum-1.4
- DOI:
- 10.18653/v1/2023.newsum-1.4
- Cite (ACL):
- Shuo Guan and Vishakh Padmakumar. 2023. Extract, Select and Rewrite: A Modular Sentence Summarization Method. In Proceedings of the 4th New Frontiers in Summarization Workshop, pages 41–48, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Extract, Select and Rewrite: A Modular Sentence Summarization Method (Guan & Padmakumar, NewSum 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.newsum-1.4.pdf