Abstract
We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text. These encoders are connected to a single decoder, trained end-to-end using reinforcement learning to generate a focused and coherent summary. Empirical results demonstrate that multiple communicating encoders lead to a higher quality summary compared to several strong baselines, including those based on a single encoder or multiple non-communicating encoders.- Anthology ID:
- N18-1150
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Marilyn Walker, Heng Ji, Amanda Stent
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1662–1675
- Language:
- URL:
- https://aclanthology.org/N18-1150
- DOI:
- 10.18653/v1/N18-1150
- Cite (ACL):
- Asli Celikyilmaz, Antoine Bosselut, Xiaodong He, and Yejin Choi. 2018. Deep Communicating Agents for Abstractive Summarization. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1662–1675, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Deep Communicating Agents for Abstractive Summarization (Celikyilmaz et al., NAACL 2018)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/N18-1150.pdf
- Data
- CNN/Daily Mail, New York Times Annotated Corpus