Sense disambiguation of English simple prepositions in the context of English-Hindi machine translation system

Abstract

In the context of developing a Machine Translation System, the identification of the correct sense of each and every word in the document to be translated is extremely important. Adpositons play a vital role in the determination of the sense of a particular word in a sentence as they link NPs with the VPs. In the context of developing English to Hindi Machine Translation system, the transfer of the senses of each Preposition into the target langue needs done with much attention. The linguistic and grammatical role of a preposition is to express a variety of syntactic and semantic relationships between nouns, verbs, adjectives, and adverbs. Here we have selected the most important and most frequently used English simple prepositions such as ‘at’, ‘by’, ‘from’, ‘for’, ‘in’, ‘of’, ‘on’, ‘to’ and ‘with’ for the sake of contrast. A supervised machine learning approach called Support Vector Machine (SVM) is used for disambiguating the senses of the simple preposition ‘at’ in contrast with Hindi postpositions.