Title :
Personalized Question Answering System Based on Ontology and Semantic Web
Author :
Zhang, Pengfei ; Wu, Chunhua ; Wang, Cong ; Huang, Xiaohong
Author_Institution :
Center of Intell. Sci. & Technol. Res., Beijing Univ. of Posts & Telecommun., Beijing
Abstract :
Semantic Web technologies bring new benefits to knowledge-based question answering system. Especially, ontology is becoming the pivotal methodology to represent domain-specific conceptual knowledge in order to promote the semantic capability of a QA system. In this paper we present a QA system in which the domain knowledge is represented by means of ontology. In addition, personalized services are enabled through modeling users´ profiles in the form of ontology, and a Chinese natural language human-machine interface is implemented mainly through a NL parser in this system. An initial evaluation result shows the feasibility to build such a semantic QA system based on ontology, the effectivity of personalized semantic QA, the extensibility of ontology and knowledge base, and the possibility of self-produced knowledge based on semantic relations in the ontology.
Keywords :
Java; computer aided instruction; computer science education; grammars; information retrieval; information retrieval systems; natural language interfaces; object-oriented programming; ontologies (artificial intelligence); semantic Web; Chinese natural language human-machine interface; JavaTeller; domain-specific conceptual knowledge; knowledge-based question answering system; natural language parser; ontology; personalized question answering system; personalized service; self-produced knowledge; semantic Web; semantic capability; semantic relation; user profile modeling; Information resources; Java; Knowledge representation; Man machine systems; Natural languages; Ontologies; Robustness; Semantic Web; Terminology; User interfaces;
Conference_Titel :
Industrial Informatics, 2006 IEEE International Conference on
Conference_Location :
Singapore
Print_ISBN :
0-7803-9700-2
Electronic_ISBN :
0-7803-9701-0
DOI :
10.1109/INDIN.2006.275742