Abstract
We consider the problem of topic-focused abstractive summarization, where the goal is to generate an abstractive summary focused on a particular topic, a phrase of one or multiple words. We hypothesize that the task of generating topic-focused summaries can be improved by showing the model what it must not focus on. We introduce a deep reinforcement learning approach to topic-focused abstractive summarization, trained on rewards with a novel negative example baseline. We define the input in this problem as the source text preceded by the topic. We adapt the CNN-Daily Mail and New York Times summarization datasets for this task. We then show through experiments on existing rewards that the use of a negative example baseline can outperform the use of a self-critical baseline, in Rouge, BERTScore, and human evaluation metrics.- Anthology ID:
- 2021.newsum-1.4
- Volume:
- Proceedings of the Third Workshop on New Frontiers in Summarization
- Month:
- November
- Year:
- 2021
- Address:
- Online and in Dominican Republic
- Venue:
- newsum
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 33–38
- Language:
- URL:
- https://aclanthology.org/2021.newsum-1.4
- DOI:
- 10.18653/v1/2021.newsum-1.4
- Cite (ACL):
- Khalil Mrini, Can Liu, and Markus Dreyer. 2021. Rewards with Negative Examples for Reinforced Topic-Focused Abstractive Summarization. In Proceedings of the Third Workshop on New Frontiers in Summarization, pages 33–38, Online and in Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Rewards with Negative Examples for Reinforced Topic-Focused Abstractive Summarization (Mrini et al., newsum 2021)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.newsum-1.4.pdf