Double Graph Based Reasoning for Document-level Relation Extraction

Understand

Document-level relation extraction aims to extract relations among entities within a document.

• Different from sentence-level relation extraction, it requires reasoning over multiple sentences across a document.
• In this paper, we propose Graph Aggregation-and-Inference Network (GAIN) featuring double graphs.
• GAIN first constructs a heterogeneous mention-level graph (hMG) to model complex interaction among different mentions across the document.