Key Issues

In the closing session, the participants discussed what they saw as the most important research questions and challenges. Six emerged as priorities:

1. How can we more efficiently evaluate the quality of predictive models and the systems which use them?
2. Many aspects of human communication dynamics are interesting, but which are the ones that really matter, in human-human interactions and for systems that interact with people?
3. How can we make it easier to effectively use the findings of the various component research fields, scattered and hard to access as they are?
4. Assuming that we can build predictive models, how can we use their output in decision-making for dialog systems and other applications?
5. We have good algorithms for processing words and good algorithms for processing non-symbolic signals, but how can we cleanly combine symbolic and non-symbolic information, as the need arises in recognition, in prediction, and in behavior synthesis?
6. What methods do humans use to predict/simulate the near future in dialog, and how accurate are they?