Incorporating Discourse Aspects in English - Polish MT: Towards Robust Implementation

The main aim of translation is an accurate transfer of meaning so that the result is not only grammatically and lexically correct but also communicatively adequate. This paper stresses the need for discourse analysis the aim of which is to preserve the communicative meaning in English--Polish machine translation. Unlike English, which is a positional language with word order grammatically determined, Polish displays a strong tendency to order constituents according to their degree of salience, so that the most informationally salient elements are placed towards the end of the clause regardless of their grammatical function. The Centering Theory developed for tracking down given information units in English and the Theory of Functional Sentence Perspective predicting informativeness of subsequent constituents provide theoretical background for this work. The notion of {\em center} is extended to accommodate not only for pronominalisation and exact reiteration but also for definiteness and other center pointing constructs. Center information is additionally graded and applicable to all primary constituents in a given utterance. This information is used to order the post-transfer constituents correctly, relying on statistical regularities and some syntactic clues.