In this work, we study the effectiveness of state-of-the-art, sophisticated supervised learning algorithms for dialogue act modeling across a comprehensive set of different spoken and written conversations including: emails, forums, meetings, and phone conversations. To this aim, we compare the results of SVM-multiclass and two structured predictors namely SVMhmm and CRF algorithms. Extensive empirical results, across different conversational modalities, demonstrate the effectiveness of our SVM-hmm model for dialogue act recognition in conversations.
Dialogue Act Recognition in Synchronous and Asynchronous Conversations
Maryam Tavafi, Yashar Mehdad, Shafiq Joty, Giuseppe Carenini, and Raymond Ng. In Proceedings of the Special Interest Group on Discourse and Dialogue Conference (SIGDIAL'13) , pages 117-121, 2013.
PDF Abstract BibTex Slides