Comparative Analysis of Phrase Based, Hierarchical and Syntax Based Statistical Machine Translation

Abstract

Languages have inherent property of tree-based recursive arrangement of phrases and follow a syntactic grammar. Phrase Based Translation is considered state-of-the-art in the field of statistical machine translation, but does not take into account the above mentioned properties of languages. Hierarchical and Syntax based machine translations are aimed to model these properties of languages. English-Hindi language pair, belonging to two different language families needs conversion of Subject-Verb-Object (SVO) structure of English to Subject-Object-Verb (SOV) structure of Hindi. This paper is aimed to perform comparative analysis of these models for this language pair which demands long distance movement of words or phrases.