Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction
This work addresses document-level relation extraction, a key task in natural language processing, by introducing a novel method to model entity dependencies, though it is incremental in improving existing attention-based approaches.
The paper tackled the problem of modeling entity structure for document-level relation extraction by formulating dependencies between mention pairs and proposing SSAN, which incorporates these dependencies within self-attention mechanisms, achieving new state-of-the-art results on three datasets.
Entities, as the essential elements in relation extraction tasks, exhibit certain structure. In this work, we formulate such structure as distinctive dependencies between mention pairs. We then propose SSAN, which incorporates these structural dependencies within the standard self-attention mechanism and throughout the overall encoding stage. Specifically, we design two alternative transformation modules inside each self-attention building block to produce attentive biases so as to adaptively regularize its attention flow. Our experiments demonstrate the usefulness of the proposed entity structure and the effectiveness of SSAN. It significantly outperforms competitive baselines, achieving new state-of-the-art results on three popular document-level relation extraction datasets. We further provide ablation and visualization to show how the entity structure guides the model for better relation extraction. Our code is publicly available.