Abstract. This paper presents our efforts to create argument structures from meeting transcripts automatically. We show that unit labels of argument diagrams can be learnt and pred...
This paper presents a restricted version of Set-Local Multi-Component TAGs Weir, 1988 which retains the strong generative capacity of Tree-Local MultiComponent TAG i.e. produces t...
In this paper we present the geometrical construction of an approximate generalized Voronoi diagram for generalized polygons and circular objects based on their minimum geometrica...
This paper presents a model for generating prosodically appropriate synthesized responses to database queries using Combinatory Categorial Grammar (CCG - cf. [22]), a formalism wh...
We study metric learning as a problem of information retrieval. We present a general metric learning algorithm, based on the structural SVM framework, to learn a metric such that ...