Abstract
Continual relation extraction (CRE) aims to solve the problem of catastrophic forgetting when learning a sequence of newly emerging relations. Recent CRE studies have found that catastrophic forgetting arises from the model’s lack of robustness against future analogous relations. To address the issue, we introduce rationale, i.e., the explanations of relation classification results generated by Large Language Models (LLM), into CRE task. Specifically, we design the multi-task rationale tuning strategy to help the model learn current relations robustly. We also conduct contrastive rationale replay to further distinguish analogous relations. Experimental results on two standard benchmarks demonstrate that our method outperforms the state-of-the-art CRE models.- Anthology ID:
- 2023.emnlp-main.958
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 15489–15497
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2023.emnlp-main.958/
- DOI:
- 10.18653/v1/2023.emnlp-main.958
- Cite (ACL):
- Weimin Xiong, Yifan Song, Peiyi Wang, and Sujian Li. 2023. Rationale-Enhanced Language Models are Better Continual Relation Learners. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15489–15497, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Rationale-Enhanced Language Models are Better Continual Relation Learners (Xiong et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2023.emnlp-main.958.pdf