Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization

Jiawen Xie, Qi Su, Shaoting Zhang, Xiaofan Zhang


Abstract
Most Transformer based abstractive summarization systems have a severe mismatch between training and inference, i.e., exposure bias. From diverse perspectives, we introduce a simple multi-level contrastive learning framework for abstractive summarization (SimMCS) and a tailored sparse decoder self-attention pattern (SDSA) to bridge the gap between training and inference to improve model performance. Compared with previous contrastive objectives focusing only on the relative order of probability mass assigned to non-gold summaries, SimMCS additionally takes their absolute positions into account, which guarantees that the relatively high-quality (positive) summaries among them could be properly assigned high probability mass, and further enhances the capability of discriminating summary quality beyond exploiting potential artifacts of specific metrics. SDSA simulates the possible inference scenarios of deviation in the training phase to get closer to the ideal paradigm. Our approaches outperform the previous state-of-the-art results on two summarization datasets while just adding fairly low overhead. Further empirical analysis shows our model preserves the advantages of prior contrastive methods and possesses strong few-shot learning ability.
Anthology ID:
2023.findings-acl.617
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9732–9747
Language:
URL:
https://aclanthology.org/2023.findings-acl.617
DOI:
10.18653/v1/2023.findings-acl.617
Bibkey:
Cite (ACL):
Jiawen Xie, Qi Su, Shaoting Zhang, and Xiaofan Zhang. 2023. Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9732–9747, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization (Xie et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.617.pdf