Welcome to the InfoSci Platform
Reference Hub5
Biomedical Ontology Matching Through Attention-Based Bidirectional Long Short-Term Memory Network

Biomedical Ontology Matching Through Attention-Based Bidirectional Long Short-Term Memory Network

Xingsi Xue, Chao Jiang, Jie Zhang, Cong Hu
Copyright: © 2021 |Volume: 32 |Issue: 4 |Pages: 14
ISSN: 1063-8016|EISSN: 1533-8010|EISBN13: 9781799859116|DOI: 10.4018/JDM.2021100102
Cite Article Cite Article

MLA

Xue, Xingsi, et al. "Biomedical Ontology Matching Through Attention-Based Bidirectional Long Short-Term Memory Network." JDM vol.32, no.4 2021: pp.14-27. http://doi.org/10.4018/JDM.2021100102

APA

Xue, X., Jiang, C., Zhang, J., & Hu, C. (2021). Biomedical Ontology Matching Through Attention-Based Bidirectional Long Short-Term Memory Network. Journal of Database Management (JDM), 32(4), 14-27. http://doi.org/10.4018/JDM.2021100102

Chicago

Xue, Xingsi, et al. "Biomedical Ontology Matching Through Attention-Based Bidirectional Long Short-Term Memory Network," Journal of Database Management (JDM) 32, no.4: 14-27. http://doi.org/10.4018/JDM.2021100102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Biomedical ontology formally defines the biomedical entities and their relationships. However, the same biomedical entity in different biomedical ontologies might be defined in diverse contexts, resulting in the problem of biomedicine semantic heterogeneity. It is necessary to determine the mappings between heterogeneous biomedical entities to bridge the semantic gap, which is the so-called biomedical ontology matching. Due to the plentiful semantic meaning and flexible representation of biomedical entities, the biomedical ontology matching problem is still an open challenge in terms of the alignment's quality. To face this challenge, in this work, the biomedical ontology matching problem is deemed as a binary classification problem, and an attention-based bidirectional long short-term memory network (At-BLSTM)-based ontology matching technique is presented to address it, which is able to capture the semantic and contextual feature of biomedical entities. In the experiment, the comparisons with state-of-the-art approaches show the effectiveness of the proposal.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.