Abstract: Source language text from an input interface is broken down into source language morphemes by a morphological analyzer. A syntactic analyzer converts the morphemes into source language signs labelled with identifiers and data identifying other signs which are grammatically related. A bilingual equivalence transformer transforms the source language signs to target language signs which are combined by a combiner to provide a first attempt at a target language structure. The structure is repeatedly evaluated by an evaluator and transformed by a transformer. The signs of well formed substructures identified by the evaluator are not dissociated from each other by the transformer. This process ends when either the whole target language structure is evaluated as being well formed or all transformations have been unsuccessfully evaluated.