Abstract
Standard extractive systems suffer from the lack of gold training signals since existing corpora solely provide document and human-written summary pairs while disregarding extractive labels. As a result, existing methods resort to imperfect pseudo-labels that are both biased and error-prone, thereby hindering the learning process of extractive models. In contrast, text generators which are commonly employed in abstractive summarization can effortlessly overcome this predicament on account of flexible sequence-to-sequence architectures. Motivated to bypass this inherent limitation, we investigate the possibility of conducting extractive summarization with text generators. Through extensive experiments covering six summarization benchmarks, we show that high-quality extractive summaries can be assembled via approximating the outputs (abstractive summaries) of these generators. Moreover, we find that the approximate summaries correlate positively with the auxiliary summaries (i.e. a better generator enables the production of better extractive summaries). Our results signify a new paradigm for training extractive summarizers i.e. learning with generation (abstractive) objectives rather than extractive schemes.- Anthology ID:
- 2024.naacl-long.9
- Volume:
- Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Kevin Duh, Helena Gomez, Steven Bethard
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 157–174
- Language:
- URL:
- https://aclanthology.org/2024.naacl-long.9
- DOI:
- Cite (ACL):
- Thang Le and Anh Tuan Luu. 2024. Extractive Summarization with Text Generator. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 157–174, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Extractive Summarization with Text Generator (Le & Luu, NAACL 2024)
- PDF:
- https://preview.aclanthology.org/ingestion-checklist/2024.naacl-long.9.pdf