Abstract:
Cross Lingual Word Semantic (CLWS) similarity is defined as a task to find the semantic similarity between two words across languages. Semantic similarity has been very popular in computing the similarity between two words in same language. CLWS similarity will prove to be very effective in the area of Cross Lingual Information Retrieval, Machine Translation, Cross Lingual Word Sense Disambiguation, etc. In this paper, we discuss a system that is developed to compute CLWS similarity of words between two languages, where one language is treated as resourceful and other is resource scarce. The system is developed using WordNet. The intuition behind this system is that, two words are semantically similar if their senses are similar to each other. The system is tested for English and Hindi with the accuracy 60.5 percent precision at 1 and 72.91 percent preci sion at 3.
