Robust processing of the Dutch verb phrase

Abstract

Abstract The Dutch verb phrase (VP) is notorious for its syntactic intricacies. There are three main reasons why it is difficult to robustly handle its complexity in a processing model. First of all, a single VP can contain multiple modal auxiliaries (‘modal stacking’). Second, perfect auxiliaries can not only take a past participle as their argument but also a modal auxiliary in the infinitive form. Finally, there are various word orders in which the verb forms can appear. The first part of this paper presents a fully operational precision processing model of the Dutch VP in Fluid Construction Grammar. The model shows that the aforementioned challenges can be overcome by carefully managing the hierarchical relations between the elements of the VP. The second part introduces a robust comprehension method, which can process VPs containing morphological and word order errors. This method allows in many cases to recover the intended meaning of an erroneous VP, as well as to correct its form, using a strategy that exploits the deep semantic analyses and the bidirectional nature of the model.