Contrasting the Interaction Structure of an Email and a Telephone Corpus: A Machine Learning Approach to Annotation of Dialogue Function Units

Jun Hu, Rebecca J. Passonneau and Owen Rambow

SIGDIAL Workshop on Discourse and Dialogue (SIGDIAL 2009)
Queen Mary University of London, September 11-12, 2009

Summary

We present a dialogue annotation scheme for both spoken and written interaction, and compare its application to a telephone transaction corpus and an email corpus. We train classifiers for both corpora, comparing regular SVM and structured SVM against a heuristic baseline. We provide a novel application of structured SVM to predicting relations between instance pairs.