We examine the utility of speech and lexical features for predicting student emotions in computerhuman spoken tutoring dialogues. We first annotate student turns for negative, neu...
The disclosure of audio-visual meeting recordings is a new challenging domain studied by several large scale research projects in Europe and the US. Automatic meeting summarizatio...
Anne Hendrik Buist, Wessel Kraaij, Stephan Raaijma...
In most research on concept acquisition from corpora, concepts are modeled as vectors of relations extracted from syntactic structures. In the case of modifiers, these relations o...
Music has structure at many levels, from grand arrangements of verses and choruses down to patterns in small riffs and themes. A bracketed L-system -- the SARAH language -- is use...
We describe our criterion-referenced grading scheme for a first year programming subject, which has been designed to allow all participating students to achieve their full potenti...