DocumentCode
3331540
Title
An expectation-driven approach to Q-A processing in a mixed-initiative natural language interface
Author
Wallfesh, Saundra K. ; Shin, Dong-Guk
Author_Institution
Dept. of Comput. Sci. & Eng., Connecticut Univ., Storrs, CT, USA
fYear
1989
fDate
6-10 Mar 1989
Firstpage
67
Lastpage
74
Abstract
In a mixed-initiative natural-language interface, questions are essentially requests for information. Expectations about the nature of the information requested accompany such questions. The system needs a way of determining whether the user has adequately answered its question. An expectation-based approach to this aspect of question-answer understanding is shown to be a viable strategy. The authors discuss representing and extracting these expectations from system questions and then subsequently using them to evaluate user answers to these questions
Keywords
knowledge engineering; natural languages; user interfaces; Q-A processing; expectation-driven; knowledge engineering; mixed-initiative natural language interface; question-answer understanding; system questions; user interfaces; Computer science; Data engineering; Data mining; Databases; Expert systems; Humans; Mesons; Natural languages; Project management;
fLanguage
English
Publisher
ieee
Conference_Titel
Artificial Intelligence Applications, 1989. Proceedings., Fifth Conference on
Conference_Location
Miami, FL
Print_ISBN
0-8186-1902-3
Type
conf
DOI
10.1109/CAIA.1989.49138
Filename
49138
Link To Document