Summary of the paper
| Title | Wizard of Oz Experiments for a Companion Dialogue System: Eliciting Companionable Conversation |
|---|---|
| Authors | Nick Webb, David Benyon, Jay Bradley, Preben Hansen and Oil Mival |
| Abstract | Within the EU-funded COMPANIONS project, we are working to evaluate newcollaborative conversational models of dialogue. Such an evaluation requires usto benchmark approaches to companionable dialogue. In order to determine theimpact of system strategies on our evaluation paradigm, we need to generate arange of companionable conversations, using dialogue strategies such as`empathy' and `positivity'. By companionable dialogue, we mean interactionsthat take user input of some scenario, and respond in a manner appropriate tothe emotional content of the user utterance. In this paper, we describe ourworking Wizard of Oz (WoZ) system for systematically creating dialogues thatfulfil these potential strategies, and enables us to deploy a range ofpotential techniques for selecting which parts of user input to address iswhich order, to inform the wizard response to the user based on a manual,on-the-fly assessment of the polarity of the user input. |
| Language | Emotion Recognition/Generation |
| Topics | Dialogue, Corpus (creation, annotation, etc.), Emotion Recognition/Generation |
Full paper  |
Wizard of Oz Experiments for a Companion Dialogue System: Eliciting Companionable Conversation |
| Bibtex | @InProceedings{WEBB10.435, author = {Nick Webb, David Benyon, Jay Bradley, Preben Hansen and Oil Mival}, title = {Wizard of Oz Experiments for a Companion Dialogue System: Eliciting Companionable Conversation}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |