English

Mention-centered Graph Neural Network for Document-level Relation Extraction

Computation and Language 2021-03-16 v1 Artificial Intelligence

Abstract

Document-level relation extraction aims to discover relations between entities across a whole document. How to build the dependency of entities from different sentences in a document remains to be a great challenge. Current approaches either leverage syntactic trees to construct document-level graphs or aggregate inference information from different sentences. In this paper, we build cross-sentence dependencies by inferring compositional relations between inter-sentence mentions. Adopting aggressive linking strategy, intermediate relations are reasoned on the document-level graphs by mention convolution. We further notice the generalization problem of NA instances, which is caused by incomplete annotation and worsened by fully-connected mention pairs. An improved ranking loss is proposed to attend this problem. Experiments show the connections between different mentions are crucial to document-level relation extraction, which enables the model to extract more meaningful higher-level compositional relations.

Keywords

Cite

@article{arxiv.2103.08200,
  title  = {Mention-centered Graph Neural Network for Document-level Relation Extraction},
  author = {Jiaxin Pan and Min Peng and Yiyan Zhang},
  journal= {arXiv preprint arXiv:2103.08200},
  year   = {2021}
}
R2 v1 2026-06-24T00:09:18.242Z