[go: up one dir, main page]

Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction

Mengting Hu, Yinhao Bai, Yike Wu, Zhen Zhang, Liqi Zhang, Hang Gao, Shiwan Zhao, Minlie Huang


Abstract
Recently, aspect sentiment quad prediction has received widespread attention in the field of aspect-based sentiment analysis. Existing studies extract quadruplets via pre-trained generative language models to paraphrase the original sentence into a templated target sequence. However, previous works only focus on what to generate but ignore what not to generate. We argue that considering the negative samples also leads to potential benefits. In this work, we propose a template-agnostic method to control the token-level generation, which boosts original learning and reduces mistakes simultaneously. Specifically, we introduce Monte Carlo dropout to understand the built-in uncertainty of pre-trained language models, acquiring the noises and errors. We further propose marginalized unlikelihood learning to suppress the uncertainty-aware mistake tokens. Finally, we introduce minimization entropy to balance the effects of marginalized unlikelihood learning. Extensive experiments on four public datasets demonstrate the effectiveness of our approach on various generation templates.
Anthology ID:
2023.findings-acl.851
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:
13481–13494
Language:
URL:
https://aclanthology.org/2023.findings-acl.851
DOI:
10.18653/v1/2023.findings-acl.851
Bibkey:
Cite (ACL):
Mengting Hu, Yinhao Bai, Yike Wu, Zhen Zhang, Liqi Zhang, Hang Gao, Shiwan Zhao, and Minlie Huang. 2023. Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13481–13494, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction (Hu et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.851.pdf