Machine Translation (MT) refers to the use of a machine for performing translation task which converts text or speech from one Natural Language (NL) into another Natural Language. This is a multiphase process.
Due to ambiguity of natural languages which are caused by multiple meaning words, use of pronouns and phrases, incomplete sentences, syntactic and semantic ambiguities the task of machine translation is very challenging. The knowledge structure of source and target language is different and detail knowledge of both the languages are to be formalized for the task of machine translation. There are various approaches of MT which are : rule based, statistical, example based, dictionary based, hybrid etc. These approaches use various knowledge structures for the MT.
To increase the accuracy of the MT output various intelligent knowledge representation schemes are used which help in removing the ambiguity of the language and increases the well defined property of the text.


Author: Dr. Madhavi Sinha