Supervised, Unsupervised and Semi-Supervised Word Sense Disambiguation Approaches

Abstract

Word Sense Disambiguation (WSD) aims to help humans figure out what a word means when used in a certain setting. According to the Neuro Linguistic Programming (NLP) community, WSD is an AI-complete issue with no human solution in sight. WSD has found widespread usage in a wide variety of applications, including but not limited to: Machine translation (MT), Information Retrieval (IR), Data Mining (DM), Information Extraction (IE), and Lexicology (Lex). It is discovered that WSD may be learned effectively using a variety of different methodologies, including supervised, semi-supervised, and unsupervised methods. These methodologies are sorted into groups according to the kind and quantity of annotated (identified) corpora (data) they need as the primary source of information utilized to distinguish between senses. The unsupervised method employs unannotated (unidentifiable) corpora for training, whereas the semi-supervised method requires a less number of annotated corpora than supervised methods. All these three strategies will critically be discussed in this study.