Abstract
Neural relation extraction models have shown promising results in recent years; however, the model performance drops dramatically given only a few training samples. Recent works try leveraging the advance in few-shot learning to solve the low resource problem, where they train label-agnostic models to directly compare the semantic similarities among context sentences in the embedding space. However, the label-aware information, i.e., the relation label that contains the semantic knowledge of the relation itself, is often neglected for prediction. In this work, we propose a framework considering both label-agnostic and label-aware semantic mapping information for low resource relation extraction. We show that incorporating the above two types of mapping information in both pretraining and fine-tuning can significantly improve the model performance on low-resource relation extraction tasks.- Anthology ID:
- 2021.emnlp-main.212
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2694–2704
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.212
- DOI:
- 10.18653/v1/2021.emnlp-main.212
- Cite (ACL):
- Manqing Dong, Chunguang Pan, and Zhipeng Luo. 2021. MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2694–2704, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction (Dong et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2021.emnlp-main.212.pdf
- Data
- FewRel, SQuAD