Interlingual machine translation

In this approach, the source language, i.e. the text to be translated is transformed into an interlingua, i.e., an abstract language-independent representation.

The obvious disadvantage is that the definition of an interlingua is difficult and maybe even impossible for a wider domain.

[2] The first ideas about interlingual machine translation appeared in the 17th century with Descartes and Leibniz, who came up with theories of how to create dictionaries using universal numerical codes, not unlike numerical tokens used by large language models nowadays.

Others, such as Cave Beck, Athanasius Kircher and Johann Joachim Becher worked on developing an unambiguous universal language based on the principles of logic and iconographs.

In 1668, John Wilkins described his interlingua in his "Essay towards a Real Character and a Philosophical Language".

That said, applying the idea of a universal language to machine translation did not appear in any of the first significant approaches.

In the 1980s, renewed relevance was given to interlingua-based, and knowledge-based approaches to machine translation in general, with much research going on in the field.

The most important research of this era was done in distributed language translation (DLT) in Utrecht, which worked with a modified version of Esperanto, and the Fujitsu system in Japan.

The system may also be set up such that the second interlingua uses a more specific vocabulary that is closer, or more aligned with the target language, and this could improve the translation quality.

It is however necessary to distinguish between interlingual systems using only syntactic methods (for example the systems developed in the 1970s at the universities of Grenoble and Texas) and those based on artificial intelligence (from 1987 in Japan and the research at the universities of Southern California and Carnegie Mellon).

One of the main advantages of this strategy is that it provides an economical way to make multilingual translation systems.

Another problem is that it is difficult to extract meaning from texts in the original languages to create the intermediate representation.

Figure 1. Demonstration of the languages which are used in the process of translating using a bridge language.
Figure 2. a) Translation graph required for direct or transfer-based machine translation (12 dictionaries are required); b) Translation graph required when using a bridge language (only 8 translation modules are required).
Figure 3: Translation graph using two interlinguas.
Figure 4. Machine translation in a knowledge-based system.