Paper: Experiments With Interactive Question-Answering

ACL ID P05-1026
Title Experiments With Interactive Question-Answering
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2005

This paper describes a novel framework for interactive question-answering (Q/A) based on predictive questioning. Gen- erated off-line from topic representations of complex scenarios, predictive ques- tions represent requests for information that capture the most salient (and diverse) aspects of a topic. We present experimen- tal results from large user studies (featur- ing a fully-implemented interactive Q/A system named FERRET) that demonstrates that surprising performance is achieved by integrating predictive questions into the context of a Q/A dialogue.