Distributional Semantic Models have been successfully used for modeling selectional preferences in a variety of scenarios, since distributional similarity naturally provides an estimate of the degree to which an argument satisfies the requirement of a given predicate. However, we argue that the performance of such models on rare verb-argument combinations has received relatively little attention: it is not clear whether they are able to distinguish the combinations that are simply atypical, or implausible, from the semantically anomalous ones, and in particular, they have never been tested on the task of modeling their differences in processing complexity. In this paper, we compare two different models of thematic fit by testing their ability of identifying violations of selectional restrictions in two datasets from the experimental studies.

This paper presents an approach to evaluate complexity of a given natural language input by means of a Fuzzy Grammar with some fuzzy logic formulations. Usually, the approaches in linguistics has described a natural language grammar by means of discrete terms. However, a grammar can be explained in terms of degrees by following the concepts of linguistic gradience & fuzziness. Understanding a grammar as a fuzzy or gradient object allows us to establish degrees of grammaticality for every linguistic input. This shall be meaningful for linguistic complexity considering that the less grammatical an input is the more complex its processing will be. In this regard, the degree of complexity of a linguistic input (which is a linguistic representation of a natural language expression) depends on the chosen grammar. The bases of the fuzzy grammar are shown here. Some of these are described by Fuzzy Type Theory. The linguistic inputs are characterized by constraints through a Property Grammar.