Representation iterative fusion based on heterogeneous graph neural network for joint entity and relation extraction

Joint entity and relation extraction is an essential task in information extraction, which aims to extract all relational triples from unstructured text. However, few existing works consider possible relations information between entities before extracting them, which may lead to the fact that most of the extracted entities cannot constitute valid triples. In this paper, we propose a representation iterative fusion based on heterogeneous graph neural networks for relation extraction (RIFRE). We model relations and words as nodes on the graph and fuse the two types of semantic nodes by the message passing mechanism iteratively to obtain nodes representation that is more suitable for relation extraction tasks. The model performs relation extraction after nodes representation is updated. We evaluate RIFRE on two public relation extraction datasets: NYT and WebNLG. The results show that RIFRE can effectively extract triples and achieve state-of-the-art performance.1 Moreover, RIFRE is also suitable for the relation classification task, and significantly outperforms the previous methods on SemEval 2010 Task 8 datasets. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes a relation extraction model RIFRE based on heterogeneous graph neural networks. Through representation iterative fusion, it successfully establishes effective connections between entities and relations, improving the accuracy and efficiency of relation extraction. Empirical results on multiple datasets have demonstrated the superior performance of RIFRE.