Lexical Based Reordering Models for English to Telugu Machine Translation

Telugu is one of the commonly spoken regional language in India. It is mostly spoken among the states of Andhra Pradesh and Telangana. In rural areas it is difficult for the people to understand the non-regional language specially while at the time of government works, land dealing transactions etc. Due to this there is a scope to develop a machine translation model from English to Telugu. The machine translation is an automatic technique of translating one language to another through Language Processing approach. To understand the Telugu language translation, the structural comparisons are done among English and Telugu languages to attain standard outcome. In this work, Lexical based reordering statistical model (LBRSM) is used for language conversion. This analyzes the language structure outcomes between word, phrase and hierarchical based models for the translation quality purpose. To maintain good quality translation TER and BLEU metrics 62.01 and 29.07 are considered for finding n-gram exact matches. From this work, the Phrase based reordering statistical model (PBRSM) achieved better results when compared with other system models in both training and testing phases.