We report on the evaluation of information structural annotation according to the Linguistic Information Structure Annotation Guidelines (LISA, (Dipper et al., 2007)). The annotat...
Abstract. We introduce the notion of regular cost functions: a quantitative extension to the standard theory of regular languages. We provide equivalent characterisations of this n...
This work investigates design choices in modeling a discourse scheme for improving opinion polarity classification. For this, two diverse global inference paradigms are used: a su...
Human languages evolve continuously, and a puzzling problem is how to reconcile the apparent robustness of most of the deep linguistic structures we use with the evidence that the...
Animesh Mukherjee, Francesca Tria, Andrea Baronche...
We use quantitative media (blogs, and news as a comparison) data generated by a large-scale natural language processing (NLP) text analysis system to perform a comprehensive and c...