Multi-relation extraction via a global-local graph convolutional network
Publication Type
Journal Article
Publication Date
1-2022
Abstract
Relation extraction (RE) extracts the semantic relations among entities in a sentence, which converts the unstructured text into structured and easy-to-understand information. Although RE has been studied over decades, it still faces two kinds of research challenges that are not well addressed thus far: 1) joint consideration of the global sentence structure and the local entity interaction, and 2) effective solution to the overlapping triplets within the same sentence. To tackle these issues, in this paper, we present globallocal graph-based convolutional network towards multi-relation extraction, GAME for short. In particular, we devise two layers of graph convolutional network (GCN) with different structures to complete the feature extraction, which effectively improves the capability of relation extraction. Moreover, we implement the GCN layers via the pure GCN model and graph attention network respectively for further comparison. Besides, we adopt a classification strategy to extract relation among entity pairs, assisting in solving the more complicated problem of overlapping triplets in RE. Extensive experiments have been conducted on two widely-used benchmark datasets, demonstrating that our model significantly outperforms several state-of-the-art methods. As a side product, we have released our data, codes and parameter settings to facilitate other researchers
Keywords
Relation extraction, overlapping triplets, graph convolution, natural language processing
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces | OS and Networks
Research Areas
Intelligent Systems and Optimization
Publication
IEEE Transactions on Big Data
Volume
8
Issue
6
First Page
1716
Last Page
1728
ISSN
2332-7790
Identifier
10.1109/TBDATA.2022.3144151
Publisher
Institute of Electrical and Electronics Engineers
Citation
CHENG, Harry; LIAO, Lizi; HU, Linmei; and NIE, Liqiang.
Multi-relation extraction via a global-local graph convolutional network. (2022). IEEE Transactions on Big Data. 8, (6), 1716-1728.
Available at: https://ink.library.smu.edu.sg/sis_research/7592