Heterogenous affinity graph inference network for document-level relation extraction

doi:10.1016/j.knosys.2022.109146

Return

Heterogenous affinity graph inference network for document-level relation extraction

2022-08-01

DOI：10.1016/j.knosys.2022.109146

Original

Save

View PDF

Abstract

En 中文

Document-level relation extraction (Doc-level RE) is a more practical and challenging task, which provides a new perspective on obtaining factual knowledge from the more complex cross-sentence text. Recent Doc-level RE, based on pre-trained language models, uses graph neural networks to implicitly model relation reasoning in a document. However, it is not perfect that the model neglects explicit reasoning clues, leading to a weak ability and a lack of capability to model long-distance relationships. In this paper, we propose to explicitly model the heterogeneous affinity graph, HAG, including a mention graph (MG) and a coreference graph (CG). We first construct CG to cluster the expressions together as a coreference array. Then, MG and CG are incorporated to capture the reasoning clues from the adjacent affinity matrix. Moreover, HAG is aggregated into an isomorphic entity graph according to the noise suppression mechanism and RGCN. Finally, the classification is established on the normalized graph to infer the relations of entity pairs. Experimental results significantly outperform baselines by nearly 1.7% similar to 2.0% in F1 on three public datasets, DocRED, DialogRE, and MPDD. We further conduct ablation experiments to demonstrate the effectiveness of the proposed approach. (c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Keywords:

Document-level relation extraction

Graph convolutional network

Relation reasoning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.