SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction

Yuxin Xiao, Zecheng Zhang, Yuning Mao, Carl Yang, Jiawei Han


Abstract
Stepping from sentence-level to document-level, the research on relation extraction (RE) confronts increasing text length and more complicated entity interactions. Consequently, it is more challenging to encode the key information sources—relevant contexts and entity types. However, existing methods only implicitly learn to model these critical information sources while being trained for RE. As a result, they suffer the problems of ineffective supervision and uninterpretable model predictions. In contrast, we propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for RE. Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately so as to enhance interpretability. By assessing model uncertainty, SAIS further boosts the performance via evidence-based data augmentation and ensemble inference while reducing the computational cost. Eventually, SAIS delivers state-of-the-art RE results on three benchmarks (DocRED, CDR, and GDA) and outperforms the runner-up by 5.04% relatively in F1 score in evidence retrieval on DocRED.
Anthology ID:
2022.naacl-main.171
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2395–2409
Language:
URL:
https://aclanthology.org/2022.naacl-main.171
DOI:
10.18653/v1/2022.naacl-main.171
Bibkey:
Cite (ACL):
Yuxin Xiao, Zecheng Zhang, Yuning Mao, Carl Yang, and Jiawei Han. 2022. SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2395–2409, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction (Xiao et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.171.pdf
Software:
 2022.naacl-main.171.software.zip
Code
 xiaoyuxin1002/sais
Data
CDRDocRED