Machine translation often use a method based on linguistic rules: words will be translated in a linguistic way, the most suitable words of the target language will replace the ones in the source language.
It is often said that the success of machine translation requires the problem of natural language understanding to be solved.
Normally, rule-based methods pase a text, usually creating an intermediary, symbolic representation, from which the text in the target language is generated. According to the nature of the intermediary representation, an approach is described as interlingual translation or transfer- based machine translation. Those methods require extensive lexicons with morphological, syntactic and semanti information, and big sets of rules.
Sources:
- Machine translation. (2009, April 27). In Wikipedia, The Free Encyclopedia. Retrieved 10:37, May 1, 2009, from http://en.wikipedia.org/w/index.php?title=Machine_translation&oldid=286449179
- Artificial Inteligent. Machine translation(book).Andy Way.Retrieved: 1 May,2009. From: http://www.springer.com/computer/artificial/journal/10590
- Teachin machine translation. Mikel L. Forcada y Juan Antonio Perez-Ortiz. Retrieved: 1 May, 2009. From: http://www.dlsi.ua.es/tmt/
- TranslationDirectory.com. Home Page. Retrieved: 1 May, 2009. From: www.translationdirectory.com/…/article1630.php
