Machine Translation Approaches and Survey for Indian Languages
This work addresses the problem of sparse data resources for machine translation in Indian languages, but it is incremental as it focuses on baseline systems without major methodological innovations.
The study analyzed the performance of state-of-the-art Phrase-based Statistical Machine Translation (SMT) on multiple Indian languages, reporting baseline systems with an average of 10% accuracy for translation into English across language pairs.
In this study, we present an analysis regarding the performance of the state-of-art Phrase-based Statistical Machine Translation (SMT) on multiple Indian languages. We report baseline systems on several language pairs. The motivation of this study is to promote the development of SMT and linguistic resources for these language pairs, as the current state-of-the-art is quite bleak due to sparse data resources. The success of an SMT system is contingent on the availability of a large parallel corpus. Such data is necessary to reliably estimate translation probabilities. We report the performance of baseline systems translating from Indian languages (Bengali, Guajarati, Hindi, Malayalam, Punjabi, Tamil, Telugu and Urdu) into English with average 10% accurate results for all the language pairs.