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

Alsuhaibani, Mohammed and Bollegala, Danushka ORCID: 0000-0003-4476-7003 (2021) Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2021. 9761163-.

Text
Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine .pdf - Published version
Download (566kB) | Preview

Official URL: http://dx.doi.org/10.1155/2021/9761163

Abstract

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.

Item Type:	Article
Uncontrolled Keywords:	Humans, Computational Biology, Classification, Semantics, Natural Language Processing, Databases, Factual, Knowledge Bases, Machine Learning
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	11 Jan 2022 16:57
Last Modified:	18 Jan 2023 21:16
DOI:	10.1155/2021/9761163
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3146236