Rewards with Negative Examples for Reinforced Topic-Focused Abstractive Summarization

Khalil Mrini, Can Liu, Markus Dreyer


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
Venues:
EMNLP | 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
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.newsum-1.4.pdf