fmLRE: A Low-Resource Relation Extraction Model Based on Feature Mapping Similarity Calculation
Peng Wang, Tong Shao, Ke Ji, Guozheng Li, Wenjun Ke
Abstract
Low-resource relation extraction (LRE) aims to extract relations from limited labeled corpora. Existing work takes advantages of self-training or distant supervision to expand the limited labeled data in the data-driven approaches, while the selection bias of pseudo labels may cause the error accumulation in subsequent relation classification. To address this issue, this paper proposes fmLRE, an iterative feedback method based on feature mapping similarity calculation to improve the accuracy of pseudo labels. First, it calculates the similarities between pseudo-label and real-label data of the same category in a feature mapping space based on semantic features of labeled dataset after feature projection. Then, it fine-tunes initial model according to the iterative process of reinforcement learning. Finally, the similarity is used as a threshold for screening high-precision pseudo-labels and the basis for setting different rewards, which also acts as a penalty term for the loss function of relation classifier. Experimental results demonstrate that fmLRE achieves the state-of-the-art performance compared with strong baselines on two public datasets.
BibTeX
@article{Wang_Shao_Ji_Li_Ke_2023, title={fmLRE: A Low-Resource Relation Extraction Model Based on Feature Mapping Similarity Calculation}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26605}, DOI={10.1609/aaai.v37i11.26605}, abstractNote={Low-resource relation extraction (LRE) aims to extract relations from limited labeled corpora. Existing work takes advantages of self-training or distant supervision to expand the limited labeled data in the data-driven approaches, while the selection bias of pseudo labels may cause the error accumulation in subsequent relation classification. To address this issue, this paper proposes fmLRE, an iterative feedback method based on feature mapping similarity calculation to improve the accuracy of pseudo labels. First, it calculates the similarities between pseudo-label and real-label data of the same category in a feature mapping space based on semantic features of labeled dataset after feature projection. Then, it fine-tunes initial model according to the iterative process of reinforcement learning. Finally, the similarity is used as a threshold for screening high-precision pseudo-labels and the basis for setting different rewards, which also acts as a penalty term for the loss function of relation classifier. Experimental results demonstrate that fmLRE achieves the state-of-the-art performance compared with strong baselines on two public datasets.}, number={11}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wang, Peng and Shao, Tong and Ji, Ke and Li, Guozheng and Ke, Wenjun}, year={2023}, month={Jun.}, pages={13700-13708} }