Phrase-Based Statistical Machine Translation of Hindi Poetries into English by incorporating Word Sense Disambiguation

Abstract

Statistical machine translation (SMT) is a variant of machine translation where the translations are handled with statistically defined rules. Numerous researchers have attempted to build the framework which can comprehend the different dialects to translate from one source language to another target language. However, the focus on translation of poetry is less. Reliable and rapid transliteration of the poetry is very mandatory for the execution of the computer to translate the poem from one language to another. The existing approach has several issues, such as, time consumption, quality of the translation process, and matching of similar words. To overcome these issues, we propose a phrase-based statistical machine translation (PSMT) with special adherence to word sense disambiguation (WSD). The quality of the translation is increased by sensing the ambiguous words with WSD. The Hindi WordNet along with the Lesk algorithm identifies the ambiguous words and senses the exact meaning before the phrase extraction. Finally, the proposed method is compared with machine translation schemes, such as, rule-based machine translation and transfer-based machine translation. The experimental results suggest that the proposed method performed well with the inclusion of WSD in the PSMT technique.