Welcome to the InfoSci Platform
Extracting Entity Synonymous Relations via Context-Aware Permutation Invariance

Extracting Entity Synonymous Relations via Context-Aware Permutation Invariance

Nan Yan, Subin Huang, Chao Kong
Copyright: © 2022 |Volume: 17 |Issue: 1 |Pages: 17
ISSN: 1554-1045|EISSN: 1554-1053|EISBN13: 9781799894001|DOI: 10.4018/IJITWE.288039
Cite Article Cite Article

MLA

Yan, Nan, et al. "Extracting Entity Synonymous Relations via Context-Aware Permutation Invariance." IJITWE vol.17, no.1 2022: pp.1-17. http://doi.org/10.4018/IJITWE.288039

APA

Yan, N., Huang, S., & Kong, C. (2022). Extracting Entity Synonymous Relations via Context-Aware Permutation Invariance. International Journal of Information Technology and Web Engineering (IJITWE), 17(1), 1-17. http://doi.org/10.4018/IJITWE.288039

Chicago

Yan, Nan, Subin Huang, and Chao Kong. "Extracting Entity Synonymous Relations via Context-Aware Permutation Invariance," International Journal of Information Technology and Web Engineering (IJITWE) 17, no.1: 1-17. http://doi.org/10.4018/IJITWE.288039

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Discovering entity synonymous relations is an important work for many entity-based applications. Existing entity synonymous relation extraction approaches are mainly based on lexical patterns or distributional corpus-level statistics, ignoring the context semantics between entities. For example, the contexts around ''apple'' determine whether ''apple'' is a kind of fruit or Apple Inc. In this paper, an entity synonymous relation extraction approach is proposed using context-aware permutation invariance. Specifically, a triplet network is used to obtain the permutation invariance between the entities to learn whether two given entities possess synonymous relation. To track more synonymous features, the relational context semantics and entity representations are integrated into the triplet network, which can improve the performance of extracting entity synonymous relations. The proposed approach is implemented on three real-world datasets. Experimental results demonstrate that the approach performs better than the other compared approaches on entity synonymous relation extraction task.