A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
Wan-Ting Hsu, Chieh-Kai Lin, Ming-Ying Lee, Kerui Min, Jing Tang, Min Sun
Abstract
We propose a unified model combining the strength of extractive and abstractive summarization. On the one hand, a simple extractive model can obtain sentence-level attention with high ROUGE scores but less readable. On the other hand, a more complicated abstractive model can obtain word-level dynamic attention to generate a more readable paragraph. In our model, sentence-level attention is used to modulate the word-level attention such that words in less attended sentences are less likely to be generated. Moreover, a novel inconsistency loss function is introduced to penalize the inconsistency between two levels of attentions. By end-to-end training our model with the inconsistency loss and original losses of extractive and abstractive models, we achieve state-of-the-art ROUGE scores while being the most informative and readable summarization on the CNN/Daily Mail dataset in a solid human evaluation.- Anthology ID:
- P18-1013
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 132–141
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/P18-1013/
- DOI:
- 10.18653/v1/P18-1013
- Cite (ACL):
- Wan-Ting Hsu, Chieh-Kai Lin, Ming-Ying Lee, Kerui Min, Jing Tang, and Min Sun. 2018. A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 132–141, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss (Hsu et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/P18-1013.pdf
- Data
- CNN/Daily Mail