Enhancing Low-Resource Relation Representations through Multi-View Decoupling
Chenghao Fan, Wei Wei, Xiaoye Qu, Zhenyi Lu, Wenfeng Xie, Yu Cheng, Dangyang Chen
Abstract
Recently, prompt-tuning with pre-trained language models (PLMs) has demonstrated the significantly enhancing ability of relation extraction (RE) tasks. However, in low-resource scenarios, where the available training data is scarce, previous prompt-based methods may still perform poorly for prompt-based representation learning due to a superficial understanding of the relation. To this end, we highlight the importance of learning high-quality relation representation in low-resource scenarios for RE, and propose a novel prompt-based relation representation method, named MVRE (Multi-View Relation Extraction), to better leverage the capacity of PLMs to improve the performance of RE within the low-resource prompt-tuning paradigm. Specifically, MVRE decouples each relation into different perspectives to encompass multi-view relation representations for maximizing the likelihood during relation inference. Furthermore, we also design a Global-Local loss and a Dynamic-Initialization method for better alignment of the multi-view relation-representing virtual words, containing the semantics of relation labels during the optimization learning process and initialization. Extensive experiments on three benchmark datasets show that our method can achieve state-of-the-art in low-resource settings.
BibTeX
@article{Fan_Wei_Qu_Lu_Xie_Cheng_Chen_2024, title={Enhancing Low-Resource Relation Representations through Multi-View Decoupling}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29752}, DOI={10.1609/aaai.v38i16.29752}, abstractNote={Recently, prompt-tuning with pre-trained language models (PLMs) has demonstrated the significantly enhancing ability of relation extraction (RE) tasks. However, in low-resource scenarios, where the available training data is scarce, previous prompt-based methods may still perform poorly for prompt-based representation learning due to a superficial understanding of the relation. To this end, we highlight the importance of learning high-quality relation representation in low-resource scenarios for RE, and propose a novel prompt-based relation representation method, named MVRE (Multi-View Relation Extraction), to better leverage the capacity of PLMs to improve the performance of RE within the low-resource prompt-tuning paradigm. Specifically, MVRE decouples each relation into different perspectives to encompass multi-view relation representations for maximizing the likelihood during relation inference.
Furthermore, we also design a Global-Local loss and a Dynamic-Initialization method for better alignment of the multi-view relation-representing virtual words, containing the semantics of relation labels during the optimization learning process and initialization. Extensive experiments on
three benchmark datasets show that our method can achieve
state-of-the-art in low-resource settings.}, number={16}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Fan, Chenghao and Wei, Wei and Qu, Xiaoye and Lu, Zhenyi and Xie, Wenfeng and Cheng, Yu and Chen, Dangyang}, year={2024}, month={Mar.}, pages={17968-17976} }