From word to sense embeddings: a survey on vector representations of meaning

Camacho Collados, Jose ORCID: https://orcid.org/0000-0003-1618-7239 and Pilehvar, Mohammad Taher 2018. From word to sense embeddings: a survey on vector representations of meaning. Journal of Artificial Intelligence Research 63 , pp. 743-788. 10.1613/jair.1.11259

Preview

PDF - Published Version Download (2MB) | Preview

Abstract

Over the past years, distributed semantic representations have proved to be effective and flexible keepers of prior knowledge to be integrated into downstream applications. This survey focuses on the representation of meaning. We start from the theoretical background behind word vector space models and highlight one of their major limitations: the meaning conflation deficiency, which arises from representing a word with all its possible meanings as a single vector. Then, we explain how this deficiency can be addressed through a transition from the word level to the more fine-grained level of word senses (in its broader acceptation) as a method for modelling unambiguous lexical meaning. We present a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based. Finally, this survey covers the main evaluation procedures and applications for this type of representation, and provides an analysis of four of its important aspects: interpretability, sense granularity, adaptability to different domains and compositionality.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	AI Access Foundation
ISSN:	1076-9757
Date of First Compliant Deposit:	9 August 2019
Date of Acceptance:	18 October 2018
Last Modified:	04 May 2023 12:55
URI:	https://orca.cardiff.ac.uk/id/eprint/124830

Citation Data

Cited 159 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item