The translation process requires syntactical transformations of the source language structures to the various target language structures. To deal with a matrix language representation is much easier than with a tree structure, because in a matrix language representation this transformations reduce to simple matrix products.The main idea behind Atamiri is precisely that: a matrix language representation using a formal interlingua, which allows to develop a truly multilingual machine translator, i.e. one program, one lexical and grammatical data base, supporting various languages capable of operating either as source or target language, with simultaneous translation from any source language to various target languages.
The costs for the development and implementation of N languages using language pair transfer-based MT systems is proportional to the N(N-1) translation directions in the multilingual set. While for an interlingüa-based system, like Atamiri’s technology, the costs are just proportional to the N languages. In other words, the economic advantage factor is N-1.
The Babel team, a joint initiative from Alis Technologies and the Internet Society, in June 1997 announced the first major study of the actual distribution of languages on the Internet. From 3,239 home pages containing more than 500 characters, there were 15 most frequently found languages on the Web. If we want to ensure complete cross communication between those 15 languages, we would have to cover 210 translation directions. In such an endeavor Atamiri offers a more economic solution by a factor of 14!