Automating ontology curation is a crucial task in knowledge engineering.
Prediction by machine learning techniques such as semantic embedding is a
promising direction, but the relevant research is still preliminary. In this
paper, we present a class subsumption prediction method named BERTSubs, which
uses the pre-trained language model BERT to compute contextual embeddings of
the class labels and customized input templates to incorporate contexts of
surrounding classes. The evaluation on two large-scale real-world ontologies
has shown its better performance than the state-of-the-art.
Описание
[2202.09791] Contextual Semantic Embeddings for Ontology Subsumption Prediction
%0 Generic
%1 chen2022contextual
%A Chen, Jiaoyan
%A He, Yuan
%A Jimenez-Ruiz, Ernesto
%A Dong, Hang
%A Horrocks, Ian
%D 2022
%K bert contextual_embedding contextual_representation embedding hierarchical_relation hierarchy krr myown ontology_matching oxford subsumption
%T Contextual Semantic Embeddings for Ontology Subsumption Prediction
%U http://arxiv.org/abs/2202.09791
%X Automating ontology curation is a crucial task in knowledge engineering.
Prediction by machine learning techniques such as semantic embedding is a
promising direction, but the relevant research is still preliminary. In this
paper, we present a class subsumption prediction method named BERTSubs, which
uses the pre-trained language model BERT to compute contextual embeddings of
the class labels and customized input templates to incorporate contexts of
surrounding classes. The evaluation on two large-scale real-world ontologies
has shown its better performance than the state-of-the-art.
@misc{chen2022contextual,
abstract = {Automating ontology curation is a crucial task in knowledge engineering.
Prediction by machine learning techniques such as semantic embedding is a
promising direction, but the relevant research is still preliminary. In this
paper, we present a class subsumption prediction method named BERTSubs, which
uses the pre-trained language model BERT to compute contextual embeddings of
the class labels and customized input templates to incorporate contexts of
surrounding classes. The evaluation on two large-scale real-world ontologies
has shown its better performance than the state-of-the-art.},
added-at = {2022-02-23T11:24:16.000+0100},
author = {Chen, Jiaoyan and He, Yuan and Jimenez-Ruiz, Ernesto and Dong, Hang and Horrocks, Ian},
biburl = {https://www.bibsonomy.org/bibtex/2f57b34c69223d69bda96ae893a17c893/hangdong},
description = {[2202.09791] Contextual Semantic Embeddings for Ontology Subsumption Prediction},
interhash = {f008c27ce43dee36a762a2726553b300},
intrahash = {f57b34c69223d69bda96ae893a17c893},
keywords = {bert contextual_embedding contextual_representation embedding hierarchical_relation hierarchy krr myown ontology_matching oxford subsumption},
note = {cite arxiv:2202.09791Comment: Short paper (5 pages)},
timestamp = {2022-02-23T11:24:16.000+0100},
title = {Contextual Semantic Embeddings for Ontology Subsumption Prediction},
url = {http://arxiv.org/abs/2202.09791},
year = 2022
}