Morphology based tense aspect disambiguation for sentences in Telugu to English translation

Abstract

Tense, aspect and modality identification of one language and translating them to another language is a complex task in machine translation. Gaining the knowledge about tenses of a language requires complete morphology analysis of that particular Language. Native speakers of the language contain inbuilt knowledge of morphology but training the machines with this knowledge needs more effort. In this paper, we are proposing Tense, Aspect Disambiguation for the Telugu language by exploring the frequent co-occurrence of verb inflections with context words. TAD approach is to build Tense dictionary for Telugu based on the hand written rules formed by morphology analysis and then automatically tagged each sentence of test data set with the tense to which it belongs. Tagged sentences then mapped to the grammar dictionary of English while translating. Our approach had performed on text written in WX notation1 by native speakers, which contains verb-included sentences.