Different Techniques Implemented in Gurumukhi Word Sense Disambiguation

One of the most important issues in the field of Natural Language Engineering is Word Sense Disambiguation (WSD).Gurumukhi or more commonly known as Punjabi, is world’s 12th most widely spoken language and this language is morphologically rich. But surprisingly, there are relatively less efforts in the field of computerization and development of lexical resources of this language. It is therefore motivating to develop a corpus of Punjabi Language that will help in tagging the sense of the words.The availability of sense tagged corpora contribute a lot in advances in WSD. Most accurate WSD systems use supervised learning algorithm to learn contextual rules or classification models automatically from sense-annotated examples, like Naïve Bayes, k-NN and Support Vector Machine (SVM) classifiers have shown high accuracy in WSD. The majority of work on WSD is focused on English and other European languages and standard test corpora are available for these languages. The lack of such standards put a major hindrance on WSD research for Punjabi and other Regional Indian languages. Thus, this defines the objective of this survey.