Title :
Improving query-answers from domain knowledge
Author :
Andreasen, Troels
Author_Institution :
Dept. of Comput. Sci., Roskilde Univ., Denmark
Abstract :
The paper introduces an approach to open knowledge-based query evaluation and describes a preliminary prototype taking this approach. A knowledge-base (KB), complementing the primary information base, that defines and relates words and concepts and exploits similarities between concepts, is used to improve answers. The knowledge base may introduce common and/or domain specific knowledge. The overall approach is to apply the KB in combination with a highly parameterised matching and aggregation, such that queries are transformed and expanded through the KB and parameters are resolved from the KB
Keywords :
knowledge based systems; natural languages; query processing; text analysis; KB; domain knowledge; domain specific-knowledge; highly parameterised matching; knowledge-base; open knowledge-based query evaluation; primary information base; query transformation; query-answer improvement; Computer science; Databases; Information technology; Instruction sets; Natural language processing; Natural languages; Ontologies; Prototypes; Query processing; Vehicle driving;
Conference_Titel :
Systems, Man, and Cybernetics, 2001 IEEE International Conference on
Conference_Location :
Tucson, AZ
Print_ISBN :
0-7803-7087-2
DOI :
10.1109/ICSMC.2001.972023
