Multilingual Approach to Word Sense Disambiguation Using word2vec and Sense Embedding With Semantic Cloud

Abstract

Word Sense Disambiguation(WSD) is an open problem in the area of Natural language processing. Many WSD systems uses knowledge based unsupervised approach as it bares us from using tagged corpus. But this approach depends extensively on knowledge. Enhancing the knowledge for ambiguity resolution is one of the important issues in WSD. Although Multilingual lexical resource is an asset for knowledge based systems(KBS), many KBS have not yield satisfactory results due to lack of sufficient information required for disambiguation. Multilingual information can help boost the performance of WSD in various languages. Combining lexical semantic information from different languages helps improve WSD task. We make use of Babel Net, a huge multilingual resource provider to attain the task and design a semantic word cloud to provide high performance disambiguation by imposing additional knowledge.

Keywords: Natural Language, WSD, KBS