Abstract
We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoder-decoder model equipped with a deep recurrent generative decoder (DRGN). Latent structure information implied in the target summaries is learned based on a recurrent latent random model for improving the summarization quality. Neural variational inference is employed to address the intractable posterior inference for the recurrent latent variables. Abstractive summaries are generated based on both the generative latent variables and the discriminative deterministic states. Extensive experiments on some benchmark datasets in different languages show that DRGN achieves improvements over the state-of-the-art methods.- Anthology ID:
- D17-1222
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2091–2100
- Language:
- URL:
- https://aclanthology.org/D17-1222
- DOI:
- 10.18653/v1/D17-1222
- Cite (ACL):
- Piji Li, Wai Lam, Lidong Bing, and Zihao Wang. 2017. Deep Recurrent Generative Decoder for Abstractive Text Summarization. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2091–2100, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Deep Recurrent Generative Decoder for Abstractive Text Summarization (Li et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/naacl24-info/D17-1222.pdf
- Data
- DUC 2004, LCSTS