Publication Details

Deductive Question Answering from Multiple Resources

by Waldinger, R. and Appelt, D. E. and Fry, J. and Israel, D. J. and Jarvis, P. and Martin, D. and Riehemann, S. and Stickel, M. E. and Tyson, M. and Hobbs, J. and Dungan, J. L.

in New Directions in Question Answering,

Edited by: Mark Maybury
Published by AAAI
Address: Menlo Park, CA
2004.

Abstract

Questions in natural language are answered by consulting multiple sources and inferring answers from information they provide. An automated deduction system, equipped with an axiomatic application-domain theory, serves as the coordinator for the process. Sources include data bases, Web pages, programs, and unstructured text. Answers may contain text or visualizations. Although the approach is domain-independent, many of our experiments have dealt with geographic questions.

Electronic Copies

Adobe PDF

Word

BibTeX

EndNote

Associated Projects

	Aquaint: From Question-Answering to Information Seeking Dialogs From question-answering to information-seeking dialogs.
	Deductive Composition of Multiple Data Sources A framework is being developed for composing answers to queries, using automated deduction and multi-agent information brokering, based on multiple information sources. The technology is being applied to answering geographical queries for ecological modeling, based on NASA EOSDIS satellite imagery, map data, and gazetteer information.
	Knowledge Creation Tools for DAML This project is building ontologies and tools in support of the Semantic Web, as part of the DARPA Agent Markup Language program.
	The Automatic Synthesis Of Computer Programs

AIC Personnel

	Name	Title	E-mail
	Appelt, Doug E	Senior Computer Scientist
	Fry, John S	Alumnus
	Israel, David J	Program Director
	Jarvis, Peter A	Alumnus
	Martin, David L	Senior Computer Scientist
	Riehemann, Susanne Z.	Alumnus
	Stickel, Mark E	Principal Scientist
	Tyson, Mabry	Senior Computer Scientist
	Waldinger, Richard J	Principal Scientist