Fusing external knowledge resources for natural language understanding techniques: A survey

Wang, Yuqi, Wang, Wei, Chen, Qi, Huang, Kaizhu, Nguyen, Anh ORCID: 0000-0002-1449-211X, De, Suparna and Hussain, Amir (2023) Fusing external knowledge resources for natural language understanding techniques: A survey. Information Fusion, 92. pp. 190-204.

Text
Survey (2).pdf - Author Accepted Manuscript
Access to this file is embargoed until 28 May 2024.
Download (278kB)

Official URL: http://dx.doi.org/10.1016/j.inffus.2022.11.025

Abstract

Knowledge resources, e.g. knowledge graphs, which formally represent essential semantics and information for logic inference and reasoning, can compensate for the unawareness nature of many natural language processing techniques based on deep neural networks. This paper provides a focused review of the emerging but intriguing topic that fuses quality external knowledge resources in improving the performance of natural language processing tasks. Existing methods and techniques are summarised in three main categories: (1) static word embeddings, (2) sentence-level deep learning models, and (3) contextualised language representation models, depending on when, how and where external knowledge is fused into the underlying learning models. We focus on the solutions to mitigate two issues: knowledge inclusion and inconsistency between language and knowledge. Details on the design of each representative method, as well as their strength and limitation, are discussed. We also point out some potential future directions in view of the latest trends in natural language processing research.

Item Type:	Article
Uncontrolled Keywords:	Natural language understanding, Knowledge graph, Knowledge fusion, Representation learning, Deep learning
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	09 Jan 2023 11:32
Last Modified:	07 Mar 2023 15:55
DOI:	10.1016/j.inffus.2022.11.025
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3166824