Abstract
Document-level relation extraction aims to categorize the association between any two entities within a document.We find that previous methods for document-level relation extraction are ineffective in exploiting the full potential of large amounts of training data with varied noise levels. For example, in the ReDocRED benchmark dataset, state-of-the-art methods trained on the large-scale, lower-quality, distantly supervised training data generally do not perform better than those trained solely on the smaller, high-quality, human-annotated training data. To unlock the full potential of large-scale noisy training data for document-level relation extraction, we propose TTM-RE, a novel approach that integrates a trainable memory module, known as the Token Turing Machine, with a noisy-robust loss function that accounts for the positive-unlabeled setting. The trainable memory module enhances knowledge extraction from the large-scale noisy training dataset through an explicit learning of the memory tokens and a soft integration of the learned memory tokens into the input representation, thereby improving the model’s effectiveness for the final relation classification. Extensive experiments on ReDocRED, a benchmark dataset for document-level relation extraction, reveal that TTM-RE achieves state-of-the-art performance (with an absolute F1 score improvement of over 3%). Ablation studies further illustrate the superiority of TTM-RE in other domains (the ChemDisGene dataset in the biomedical domain) and under highly unlabeled settings.- Anthology ID:
- 2024.acl-long.26
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 443–458
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.26
- DOI:
- 10.18653/v1/2024.acl-long.26
- Cite (ACL):
- Chufan Gao, Xuan Wang, and Jimeng Sun. 2024. TTM-RE: Memory-Augmented Document-Level Relation Extraction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 443–458, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- TTM-RE: Memory-Augmented Document-Level Relation Extraction (Gao et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/landing_page/2024.acl-long.26.pdf