A Supervised Word Sense Disambiguation for Persian Using k-NN Approach

Abstract

Natural language processing (NLP) is considered as one of the most important subfields of Artificial Intelligence. It is used to provide an Interface between Computer and Human languages. NLP has found its application on several areas such as Speech processing, Summation of text, Machine translation, Searching, Information grouping, Parts of Speech Tagging (POS), Sentiment analysis and etc. Natural language processing is posing some challenges in speech recognition, ambiguity in preposition attachment, co-reference resolution, Information extraction, question answering, word sense disambiguation (WSD) and etc. Many Algorithms have been proposed so far to address the mentioned Problems in NLP and some techniques for WSD too. Word sense disambiguation (WSD) is the process of finding correct sense for a word from a collection of semantic tags (senses) in a sentence. It has application in Machine translation, Information retrieval, Information extraction and knowledge acquisition.  Along with the other languages like English, Spanish, French, Hindi that are the focus point for most of the researchers some work has been done for Persian language too. WSD for Persian need to be further researched to get more accuracy (measured by precision and recall). In this work we have applied supervised technique after pre-processing using a fully sense tagged corpus on data.

Keywords: Natural language processing, word sense disambiguation, Ambiguity, Persian language

Cite this Article
Suliman Ameryani, Nirav M. Raja, Vishal Prajapati. A Supervised Word SenseDisambiguation for Persian Using k-NN Approach. Journal of Advancements in Robotics. 2018; 5(2): 28–36p.