Towards Integration of Discriminability and Robustness for Document-Level Relation Extraction

Jia Guo, Stanley Kok, Lidong Bing


Abstract
Document-level relation extraction (DocRE) predicts relations for entity pairs that rely on long-range context-dependent reasoning in a document. As a typical multi-label classification problem, DocRE faces the challenge of effectively distinguishing a small set of positive relations from the majority of negative ones. This challenge becomes even more difficult to overcome when there exists a significant number of annotation errors in the dataset. In this work, we aim to achieve better integration of both the discriminability and robustness for the DocRE problem. Specifically, we first design an effective loss function to endow high discriminability to both probabilistic outputs and internal representations. We innovatively customize entropy minimization and supervised contrastive learning for the challenging multi-label and long-tailed learning problems. To ameliorate the impact of label errors, we equipped our method with a novel negative label sampling strategy to strengthen the model robustness. In addition, we introduce two new data regimes to mimic more realistic scenarios with annotation errors and evaluate our sampling strategy. Experimental results verify the effectiveness of each component and show that our method achieves new state-of-the-art results on the DocRED dataset, its recently cleaned version, Re-DocRED, and the proposed data regimes.
Anthology ID:
2023.eacl-main.191
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2606–2617
Language:
URL:
https://aclanthology.org/2023.eacl-main.191
DOI:
10.18653/v1/2023.eacl-main.191
Bibkey:
Cite (ACL):
Jia Guo, Stanley Kok, and Lidong Bing. 2023. Towards Integration of Discriminability and Robustness for Document-Level Relation Extraction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2606–2617, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Towards Integration of Discriminability and Robustness for Document-Level Relation Extraction (Guo et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.191.pdf
Video:
 https://aclanthology.org/2023.eacl-main.191.mp4