Interlingual machine translation

From Wikipedia, the free encyclopedia

Interlingual machine translation is one instance of rule-based machine translation approaches. According to this approach, the source language, i.e. the text to be translated is transformed into an interlingual, ie. language independent representation. The target language is then generated out of the interlingua. The idea was first discussed extensively by the Israeli philosopher Yehoshua Bar-Hillel in 1969, and his arguments still have relevance for a spectrum of methods for translating content into something abstract, not only machine translation but the translation-to-logic methods at the heart of Artificial Intelligence.

The interlingual approach to machine translation has advantages and disadvantages. The advantages in multilingual machine translations is that no transfer component has to be created for each language pair. The obvious disadvantage is that the definition of an interlingual is difficult and maybe even impossible for a wider domain. The ideal context for interlingual machine translation is thus multilingual machine translation in a very specific domain. However, large-scale interlingual MT systems have been constructed and been very effective, the best known being the Fujitsu system in Japan. Early interlingual MT systems were built at Stanford in the 1970s by Roger Schank and Yorick Wilks; the former became the basis of a commercial system for the transfer of funds, and the latter's code is preserved in the Us Computer Museum at Boston as the first interlingual machine translation system.

Within the rule-based machine translation paradigm, the interlingual approach is an alternative to the direct approach and the transfer approach. According to the direct approach, words are translated directly without passing through an additional representation. According to the transfer approach the source language is transformed into an abstract, less language specific representation. Linguistic rules which are specific to the language pair then transform the source language representation into an abstract target language representation and from this the target sentence is generated.

De facto, however, interlingual machine translations systems are no longer considered a realistic option within the rule-based machine translation paradigm. The rule-based paradigm itself is not very popular and most research in machine translation is currently done using corpus-based approaches to machine translation. These are example-based machine translation and statistical machine translation.