Resolving Pattern Ambiguity for English to Hindi Machine Translation Using WordNet

A common belief about natural language translation is that sentences of similar structure in the source language have translations that are similar in structure in the target language too. However, with respect to English to Hindi translation, this assumption does not hold well always. At least eleven different patterns can be found in the Hindi translation of English sentences in which the main verb is “have” or any of its declensions. This poses a serious problem for designing any English to Hindi translation system. Traditionally such variations are termed as “translation divergence”. Typically a study of divergence considers some standard translation pattern for a given input sentence structure. A translation is said to be a divergence if it deviates from this standard pattern. However, this is not the case with the abovementioned sentence structures. We term this ambiguity as “pattern ambiguity”. In this ongoing work we propose a rule-based scheme to resolve the ambiguity using word senses given by WordNet.