EEMCS EPrints Service
op den Akker, H. and Schulz, C. (2008) Exploring Features and Classifiers for Dialogue Act Segmentation. In: Machine Learning for Multimodal Interaction, MLMI 2008, 19-20 Sept 2008, Utrecht, the Netherlands. pp. 196-207. Lecture Notes in Computer Science 5237. Springer Verlag. ISBN 978-3-540-85852-2
Full text available as:
Official URL: http://dx.doi.org/10.1007/978-3-540-85853-9_18
This paper takes a classical machine learning approach to the task of Dialogue Act segmentation. A thorough empirical evaluation of features, both used in other studies as well as new ones, is performed. An explorative study to the effectiveness of different classification methods is done by looking at 29 different classifiers implemented in WEKA. The output of the developed classifier is examined closely and points of possible improvement are given.
Export this item as:
To correct this item please ask your editor
Repository Staff Only: edit this item