Modelling of Multiple Target Machine Translation of Controlled Languages Based on Language Norms and Divergences

In the context of crises in which emergency services or the general population are of different languages, effective interoperability requires not only that translations of messages and alerts be done rapidly but also, being safety critical, that there be no errors. We have developed a methodology based on linguistic norms and a supporting mathematical model for the construction of a single source controlled language to be machine translated to specific target controlled languages. In this paper we discuss in particular the architecture of our machine translation system which is based on the `canonical¿ case where there are no language divergences (identical source and target languages), and the `variant¿ cases encompassing the divergences between each target controlled language and our source controlled language. We explain the way that we classify and organize the divergences in a declarative manner so as to be incorporated in the machine translation process.