Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction

Xuming Hu, Chenwei Zhang, Yawen Yang, Xiaohe Li, Li Lin, Lijie Wen, Philip S. Yu


Abstract
Low-resource Relation Extraction (LRE) aims to extract relation facts from limited labeled corpora when human annotation is scarce. Existing works either utilize self-training scheme to generate pseudo labels that will cause the gradual drift problem, or leverage meta-learning scheme which does not solicit feedback explicitly. To alleviate selection bias due to the lack of feedback loops in existing LRE learning paradigms, we developed a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate the gradient descent direction on labeled data and bootstrap its optimization capability through trial and error. We also propose a framework called GradLRE, which handles two major scenarios in low-resource relation extraction. Besides the scenario where unlabeled data is sufficient, GradLRE handles the situation where no unlabeled data is available, by exploiting a contextualized augmentation method to generate data. Experimental results on two public datasets demonstrate the effectiveness of GradLRE on low resource relation extraction when comparing with baselines.
Anthology ID:
2021.emnlp-main.216
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2737–2746
Language:
URL:
https://aclanthology.org/2021.emnlp-main.216
DOI:
10.18653/v1/2021.emnlp-main.216
Bibkey:
Cite (ACL):
Xuming Hu, Chenwei Zhang, Yawen Yang, Xiaohe Li, Li Lin, Lijie Wen, and Philip S. Yu. 2021. Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2737–2746, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction (Hu et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.emnlp-main.216.pdf
Code
 thu-bpm/gradlre
Data
SemEval-2010 Task 8