Main menu >> Computer Science >> Human-Computer Interaction
Computer Science
Human-Computer Interaction
- Multimodal Human– Computer Interaction: Toward a Proactive Computer
- Context-Sensitive Natural Language Inferences
^ Multimodal Human– Computer Interaction: Toward a Proactive Computer
D. Roth,* T. S. Huang, D. E. Brown, D. Kriegman, S. Levinson, G. W. McConkie
National Science Foundation, Information Technology Research, IIS-00-85980
This project is based on the belief that to be more accessible to the general population, computers must be more proactive in their interactions with people. In human interaction, someone who waits for each command before making any communication attempt would be regarded as uncooperative and unhelpful. In order for a computer to be more proactive and bear its part of the burden of initiation in interactions, it must have much more real-time information about its user and algorithms that select actions based on this information rather than simply on user commands. The computer needs information about the user's current and past emotional, motivational, and cognitive state as well as the state of the task at hand. A theory is needed to guide the development of algorithms that select appropriate actions based on user and task states. This research constitutes the next steps in an attempt by the multidisciplinary team to develop this capability.
^ Context-Sensitive Natural Language Inferences
D. Roth,* A. Carlson
National Science Foundation, IIS-980163; IBM Corp
The future of intelligent human-machine interaction is in the ability to perform context-sensitive inferences. These are knowledge intensive tasks that are difficult to make without a significant learning component. This research studies a learning approach that targets knowledge intensive language understanding related tasks and directly addresses the issue of scalability. It is tailored to large-scale processes in terms of data and computation. The approach developed can be applied to support a variety of inferences of the sort required in intelligent human-machine interactions, as demonstrated in this project by development of a system that exhibits a wide coverage and accurate context-sensitive spelling correction.
