Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoning
This work improves relation extraction for documents with multiple entity mentions, but it is incremental as it builds on existing methods with novel techniques.
The paper tackled document-level relation extraction by addressing unequal contributions of coreferential mentions and lack of global interactions between entity pairs, resulting in a model that outperforms previous state-of-the-art models on benchmark datasets like DocRED, CDR, and GDA.
Document-level Relation Extraction (DRE) aims to recognize the relations between two entities. The entity may correspond to multiple mentions that span beyond sentence boundary. Few previous studies have investigated the mention integration, which may be problematic because coreferential mentions do not equally contribute to a specific relation. Moreover, prior efforts mainly focus on reasoning at entity-level rather than capturing the global interactions between entity pairs. In this paper, we propose two novel techniques, Context Guided Mention Integration and Inter-pair Reasoning (CGM2IR), to improve the DRE. Instead of simply applying average pooling, the contexts are utilized to guide the integration of coreferential mentions in a weighted sum manner. Additionally, inter-pair reasoning executes an iterative algorithm on the entity pair graph, so as to model the interdependency of relations. We evaluate our CGM2IR model on three widely used benchmark datasets, namely DocRED, CDR, and GDA. Experimental results show that our model outperforms previous state-of-the-art models.