The long road from performing word sense disambiguation to successfully using it in information retrieval: An overview of the unsupervised approach. (22nd March 2020)

• Record Type: Journal Article
• Authors: Hristea, Florentina; Colhon, Mihaela
• Is Part Of: Computational intelligence. Volume 36:Number 3(2020)
• Page Start: 1026
• Page End: 1062
• Publication Date: 2020-03-22
• Subjects: ambiguous query -- information retrieval -- Naïve Bayes model -- spectral clustering -- unsupervised word sense disambiguation -- word sense disambiguation; Artificial intelligence -- Periodicals; Computational linguistics -- Periodicals; 006.3
• DOI: 10.1111/coin.12303
• Languages: English
• ISSNs: 0824-7935

Abstract

Summary: The issue of whether or not word sense disambiguation (WSD) can improve information retrieval (IR) results has been intensely debated over the years, with many inconclusive or contradictory results and a majority of skeptical opinions. All three classes of WSD methods (supervised, unsupervised, and knowledge‐based) have been considered by the literature with respect to IR. We hereby survey the unsupervised approach which, although relatively rarely used, has provided positive results at a large scale. Unsupervised WSD has already made proof of its utility in IR and it is our belief that it still holds a promise for this field. The two main existing types of unsupervised methods for IR, which are of completely different natures, are presented, within the scientific context in which they were born, and are compared. Regardless of the gap in time between these central approaches, we are of the opinion that the unsupervised solution to the discussed problem remains the most significant for IR applications. By surveying what we consider the most promising existing approach to usage of WSD in IR, and by discussing its possible extensions, we hope to stimulate continuation of this line of research, possibly at an even more successful level.