Using a Reactive Planner as the Basis for a Dialogue Agent
Proceedings of the Thirteenth International Florida Artificial Intelligence Research Society Conference
Tools for Authoring a Dialogue Agent that Participates in Learning Studies
Proceedings of the 2007 conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work
Building a corpus and developing a question classifier to support messaging-based question answering
Proceedings of the 1st ACM International Health Informatics Symposium
| Hi-index | 0.00 |
We are investigating question-answering systems for different applications within consumer health, including health promotion and health information attainment. Our work focuses on the interaction environment afforded by text and multimedia (SMS and MMS) messaging because of the growing popularity of text messaging and because of the prevalence of devices that support it. The development of content for messaging may also better serve populations with diverse cognitive competencies, as the shorter blocks of text that are required for messaging may be easier for readers to process, especially if they have deficits in memory or vision. One of the challenges of this work is to provide an architecture that will allow our partners in public health and medicine to review or contribute to the domain content and that will allow us to use that content to drive a dialog engine, with little or no manual intervention. In this paper, we describe how we have adapted the TuTalk dialog system to create a new messaging-based question-answering system to promote healthy birth outcomes among low-income, expectant women in Milwaukee.