Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications

Word embedding models have recently shown some capability to encode hierarchical information that exists in textual data. However, such models do not explicitly encode the hierarchical structure that exists among words. In this work, we propose a method to learn hierarchical word embeddings (HWEs) i...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohammed Alsuhaibani, Danushka Bollegala
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/b586f8dd6686407b98ccb44fe586a29b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b586f8dd6686407b98ccb44fe586a29b
record_format	dspace
spelling	oai:doaj.org-article:b586f8dd6686407b98ccb44fe586a29b2021-11-29T00:56:54ZFine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications1748-671810.1155/2021/9761163https://doaj.org/article/b586f8dd6686407b98ccb44fe586a29b2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/9761163https://doaj.org/toc/1748-6718Word embedding models have recently shown some capability to encode hierarchical information that exists in textual data. However, such models do not explicitly encode the hierarchical structure that exists among words. In this work, we propose a method to learn hierarchical word embeddings (HWEs) in a specific order to encode the hierarchical information of a knowledge base (KB) in a vector space. To learn the word embeddings, our proposed method considers not only the hypernym relations that exist between words in a KB but also contextual information in a text corpus. The experimental results on various applications, such as supervised and unsupervised hypernymy detection, graded lexical entailment prediction, hierarchical path prediction, and word reconstruction tasks, show the ability of the proposed method to encode the hierarchy. Moreover, the proposed method outperforms previously proposed methods for learning nonspecialised, hypernym-specific, and hierarchical word embeddings on multiple benchmarks.Mohammed AlsuhaibaniDanushka BollegalaHindawi LimitedarticleComputer applications to medicine. Medical informaticsR858-859.7ENComputational and Mathematical Methods in Medicine, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Mohammed Alsuhaibani Danushka Bollegala Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications
description	Word embedding models have recently shown some capability to encode hierarchical information that exists in textual data. However, such models do not explicitly encode the hierarchical structure that exists among words. In this work, we propose a method to learn hierarchical word embeddings (HWEs) in a specific order to encode the hierarchical information of a knowledge base (KB) in a vector space. To learn the word embeddings, our proposed method considers not only the hypernym relations that exist between words in a KB but also contextual information in a text corpus. The experimental results on various applications, such as supervised and unsupervised hypernymy detection, graded lexical entailment prediction, hierarchical path prediction, and word reconstruction tasks, show the ability of the proposed method to encode the hierarchy. Moreover, the proposed method outperforms previously proposed methods for learning nonspecialised, hypernym-specific, and hierarchical word embeddings on multiple benchmarks.
format	article
author	Mohammed Alsuhaibani Danushka Bollegala
author_facet	Mohammed Alsuhaibani Danushka Bollegala
author_sort	Mohammed Alsuhaibani
title	Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications
title_short	Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications
title_full	Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications
title_fullStr	Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications
title_full_unstemmed	Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications
title_sort	fine-tuning word embeddings for hierarchical representation of data using a corpus and a knowledge base for various machine learning applications
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/b586f8dd6686407b98ccb44fe586a29b
work_keys_str_mv	AT mohammedalsuhaibani finetuningwordembeddingsforhierarchicalrepresentationofdatausingacorpusandaknowledgebaseforvariousmachinelearningapplications AT danushkabollegala finetuningwordembeddingsforhierarchicalrepresentationofdatausingacorpusandaknowledgebaseforvariousmachinelearningapplications
_version_	1718407668144537600

Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications

Ejemplares similares