Anusaaraka: Machine Translation in Stages

Abstract

Fully-automatic general-purpose high-quality machine translation systems (FGH-MT) are extremely difficult to build. In fact, there is no system in the world for any pair of languages which qualifies to be called FGH-MT. The reasons are not far to seek. Translation is a creative process which involves interpretation of the given text by the translator. Translation would also vary depending on the audience and the purpose for which it is meant. This would explain the difficulty of building a machine translation system. Since, the machine is not capable of interpreting a general text with sufficient accuracy automatically at present - let alone re-expressing it for a given audience, it fails to perform as FGH-MT. FOOTNOTE{The major difficulty that the machine faces in interpreting a given text is the lack of general world knowledge or common sense knowledge.} To understand the nature of the difficulty, let us consider the following sentence in Hindi: chAvala rAma khAtA hE rice(m.) Ram(m.) eats(m.) Ram eats rice. in which the karta (or the eater) is not marked. Translation to English, say, would be quite different depending on which one is the karta. (The problem is that there are no vibhakits (post-positions or case endings) to indicate which one is the karta or 'eater'. Noun-verb agreement normally helps in identifying the karta because the gender-number-person (gnp) of the verb agrees with the karta. Here, it does not help us in identifying the karta unambigously because the masculine (m.) ending of the verb tells us that the karta is masculine, and there are two masculine nouns (Ram or rice).)