Investigating Bidirectional Divergence In Lexical-Semantic Class For English-Hindi-Dravidian Translations

摘要

The fail factor of a Machine Translation system is largely governed by the degree of cross linguistic variations called divergence, which are encountered during translations. Divergence is a language dependent phenomenon. More the divergence more is the skewness in the results delivered by the MT system for the considered language pair. All work reported thus far study divergence in a unidirectional manner i.e. from Source Language (SL) to Target Language (TL). Through this paper, we aim to present a detailed exploration of bidirectional divergence found in English-Hindi-Dravidian language triplet, which has never been explored thus far. Moreover, if transparency in cross linguistic variations should be obtained, then two way divergences should not be overlooked. Toward this end, we propose the concept of balance and imbalance observed in to and fro divergence. Balanced being the case when the two way divergence is preserved on mirror while imbalance, when the same is violated. The Dravidian languages under consideration are Malayalam, Tamil, Telugu and Kannada. The divergence analysis has been dealt for the pairing of each of these languages with English based on children stories, translation books, advertisement material and official articles and documents.