Cargando…

Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus

BACKGROUND: Terminology integration at the scale of the UMLS Metathesaurus (i.e., over 200 source vocabularies) remains challenging despite recent advances in ontology alignment techniques based on neural networks. OBJECTIVES: To improve the performance of the neural network architecture we develope...

Descripción completa

Detalles Bibliográficos
Autores principales: Nguyen, Vinh, Bodenreider, Olivier
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9484765/
https://www.ncbi.nlm.nih.gov/pubmed/35672982
http://dx.doi.org/10.3233/SHTI220043
_version_ 1784791943067205632
author Nguyen, Vinh
Bodenreider, Olivier
author_facet Nguyen, Vinh
Bodenreider, Olivier
author_sort Nguyen, Vinh
collection PubMed
description BACKGROUND: Terminology integration at the scale of the UMLS Metathesaurus (i.e., over 200 source vocabularies) remains challenging despite recent advances in ontology alignment techniques based on neural networks. OBJECTIVES: To improve the performance of the neural network architecture we developed for predicting synonymy between terms in the UMLS Metathesaurus, specifically through the addition of an attention layer. METHODS: We modify our original Siamese neural network architecture with Long-Short Term Memory (LSTM) and create two variants by (1) adding an attention layer on top of the existing LSTM, and (2) replacing the existing LSTM layer by an attention layer. RESULTS: Adding an attention layer to the LSTM layer resulted in increasing precision to 92.38% (+3.63%) and F1 score to 91,74% (+1.13%), with limited impact on recall at 91.12% (−1.42%). CONCLUSIONS: Although limited, this increase in precision substantially reduces the false positive rate and minimizes the need for manual curation.
format Online
Article
Text
id pubmed-9484765
institution National Center for Biotechnology Information
language English
publishDate 2022
record_format MEDLINE/PubMed
spelling pubmed-94847652022-09-19 Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus Nguyen, Vinh Bodenreider, Olivier Stud Health Technol Inform Article BACKGROUND: Terminology integration at the scale of the UMLS Metathesaurus (i.e., over 200 source vocabularies) remains challenging despite recent advances in ontology alignment techniques based on neural networks. OBJECTIVES: To improve the performance of the neural network architecture we developed for predicting synonymy between terms in the UMLS Metathesaurus, specifically through the addition of an attention layer. METHODS: We modify our original Siamese neural network architecture with Long-Short Term Memory (LSTM) and create two variants by (1) adding an attention layer on top of the existing LSTM, and (2) replacing the existing LSTM layer by an attention layer. RESULTS: Adding an attention layer to the LSTM layer resulted in increasing precision to 92.38% (+3.63%) and F1 score to 91,74% (+1.13%), with limited impact on recall at 91.12% (−1.42%). CONCLUSIONS: Although limited, this increase in precision substantially reduces the false positive rate and minimizes the need for manual curation. 2022-06-06 /pmc/articles/PMC9484765/ /pubmed/35672982 http://dx.doi.org/10.3233/SHTI220043 Text en https://creativecommons.org/licenses/by-nc/4.0/This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/) .
spellingShingle Article
Nguyen, Vinh
Bodenreider, Olivier
Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus
title Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus
title_full Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus
title_fullStr Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus
title_full_unstemmed Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus
title_short Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus
title_sort adding an attention layer improves the performance of a neural network architecture for synonymy prediction in the umls metathesaurus
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9484765/
https://www.ncbi.nlm.nih.gov/pubmed/35672982
http://dx.doi.org/10.3233/SHTI220043
work_keys_str_mv AT nguyenvinh addinganattentionlayerimprovestheperformanceofaneuralnetworkarchitectureforsynonymypredictionintheumlsmetathesaurus
AT bodenreiderolivier addinganattentionlayerimprovestheperformanceofaneuralnetworkarchitectureforsynonymypredictionintheumlsmetathesaurus