Double Graph Based Reasoning for Document-level Relation Extraction
TL
TL;DR
This paper proposes Graph Aggregation-and-Inference Network (GAIN) featuring double graphs, based on which GAIN first constructs a heterogeneous mention-level graph (hMG) to model complex interaction among different mentions across the document and proposes a novel path reasoning mechanism to infer relations between entities.
Abstract
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. It also constructs an entity-level graph (EG), based on which we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at this https URL .
References45 items
1
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction
2
Coreferential Reasoning Learning for Language Representation
3
HIN: Hierarchical Inference Network for Document-Level Relation Extraction
4
Fine-tune Bert for DocRED with Two-step Process
5