Complements and adjuncts in machine translation

A significant number of natural language processing applications cannot work without syntactic parsing. The automatic syntactic analysis of natural language texts in turn requires an efficient method for differentiating between elements that belong to the predicate’s argument structure and those that are attached to it as adjuncts. The focus of our paper is a specific method we are working on for differentiating between verbal complements and adjuncts, which we intend to use for the elaboration of a Hungarian verbal argument structure database, particularly suited for machine translation purposes.