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

by   Jia Guo, et al.
National University of Singapore
Alibaba Group

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.


page 1

page 2

page 3

page 4


None Class Ranking Loss for Document-Level Relation Extraction

Document-level relation extraction (RE) aims at extracting relations amo...

Document-level Relation Extraction with Relation Correlations

Document-level relation extraction faces two overlooked challenges: long...

Improving Long Tailed Document-Level Relation Extraction via Easy Relation Augmentation and Contrastive Learning

Towards real-world information extraction scenario, research of relation...

Revisiting DocRED – Addressing the Overlooked False Negative Problem in Relation Extraction

The DocRED dataset is one of the most popular and widely used benchmarks...

Process-Level Representation of Scientific Protocols with Interactive Annotation

We develop Process Execution Graphs (PEG), a document-level representati...

Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

Document-level relation extraction (RE) poses new challenges compared to...

Budget Sensitive Reannotation of Noisy Relation Classification Data Using Label Hierarchy

Large crowd-sourced datasets are often noisy and relation classification...

Please sign up or login with your details

Forgot password? Click here to reset