Study of divergence for example based English-Hindi machine translation
Deepa Gupta, Niladri Chatterjee · 2001
The success of Example-Based Machine Translation (EBMT) often depends upon how efficient the adaptation scheme is. Adaptation essentially aims at modifying retrieved examples to meet the required demands of a given translation task. A key aspect of adaptation is dealing with divergence. Here one looks at any structural difference that has to be incorporated due to inherent constraints of the source and/or target language. The present work looks at adaptation of for EBMT between English and Hindi. Special attention has been given to the study of divergence by recognizing six different categories of divergence and providing schemes for identifying them.