以關鍵字作為資料擷取的方法具有簡易且符合使用者習慣的好處，這樣的查詢方法卻無法反映出文件實際上所代表的概念，而且也經常面臨無法提供適當的關鍵字而導致結果不盡滿意。使用本體論(Ontology)來進行關鍵字重建再進行擷取可有效的反映文件實際概念。現行方法中皆以關鍵字應對本體論之概念，再於本體論中推論出相關之概念以進行擴充。這些方法並未提供當關鍵字無法應對概念時該如何處置。關鍵字無法應對概念時有兩種情況，一為關鍵字在本體論中非以概念之形式存在、另一為關鍵字尚未規範於本體論內，此情況尤常見於本體論建置日久更新不及之時。
我們提出了基於本體論之場景式的查詢擴充系統來改善這些問題。我們使用場景來代表使用者之查詢情境用以取代關鍵字對應概念之方法。藉由本體論我們可推論出概念與概念在領域架構中的關係，以此關係作為基準進行關鍵字重建，再藉由場景來進行關鍵字重建。使用者查詢所用之關鍵字組可代表一個特定之查詢情境，找出與使用者查詢情境相符合之場景，將此場景之內容作為關鍵字重建之結果回應予使用者。場景式查詢擴充系統能將非本體論規範之關鍵字因使用者之查詢而逐漸找出與其與本體論有規範之相關概念，進而建立相對應之場景。故當使用者之關鍵字組使用了非本體論規範之概念時，也能做出適當之回應。

To use keyword-based information retrieval is easy and convenient for users. However, such practice may not be able to retrieve documents with the same semantic as what the users really want, not to mention if the keywords entered are appropriate or not. Retrievals using rebuilt keywords according to specific ontology always result in documents meant to be. The common method used to date is to match keywords with concepts in the ontology first and then to infer relevant concepts also in the ontology before using all these concepts for retrieval. Those methods did not solve the problems where keywords entered do not match any concepts in the ontology. Two situations may happen, that is when keywords are not matched to concepts but to slots or relations in the ontology and when they even are not specified in the ontology. The situations are common when ontology is not renewed frequently enough.

This thesis proposes an ontology-initiated scenario-specific query expansion system to solve these problems. The mechanism uses scenarios to replace the matching between concepts in the ontology and the keywords entered. The relation between two concepts in the ontology can be inferred, which regard this relation to rebuild the keyword. The user’s keyword can represent a specific scene, system find the fetch scenario to rebuild the keyword and output to user. Scenario query expansion system can find the relevant between unmatch keyword and the concept in ontology by user’s query. So when it is not a concept of ontology that the user's key word group has used, can make the proper response too.

[1] T. Berner-Lee, J.Hendler, and O.Lassila. The Semantic Web.
Scientific Ammerican, May 2001.
[2] N.F.Noy and D.L.Mcguinness, “Ontology Development 101: A
Guide to Creating Your First Ontology,” Stanford Knowledge
System Laboratory Technical Report KSL-01-05 and Stanford Medical Informatics Technical Report SMI-2001-0880, Mar. 2001.
[3] A. Gomez-Perez, O. Corcho, “Ontology Languages for the
Semantic Web,” IEEE Intellighnt Systems, pp.54-60, JAN/FEB, 2002.
[4] C.J. van Rijsbergn., ”Information Retrieval.“ Butterworths.
2nd edition, 1979.
[5] Extensible Markup Language (XML) ； available from
http://www.w3.org/XML/
[6] DARPA Agent Markup Language (DAML+OIL)； available from
http://www.daml.org
[7] Web-Ontology(WebOnt) Working Group
http://www.w3.org/2001/sw/WebOnt/
[8] Horrocks, Framk van Harmelen, Ian Horrocks, Deborah
L.McGuinness, and Peter F. Patel-Schneider, “OIL: An Ontology Infrastructure for the Semantic Web”, IEEE Intelligent System, vol.16, no.2, pp 38-45, March/April 2001.
[9] Horrocks, D.Fensel, J.broekstra, S.Decker, M.Erdmann, C.
Grble, and F.vn Harmelen, “The Ontology Inference Layer OIL”, Aug 2000, http://www.ontoknowledge.org
[10] R. Karp, V. Chaudhri, and J. Thomere, “XOL: An XML-based
Ontology Exchange Language,” Technical Report, Aug. 1999.
[11] O.Lassila and R.Swick, “Resource Description Framework(RDF)
Model and Syntax Specification,” World Wide Web Consortium Recommendation, Feb. 1999; available from http://www.w3.org/TR/REC-rdf-syntax
[12] P. Pantel, and D. Lin. “Discovering Word Senses from Text,”
In Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining pp 613-619, 2002.
[13] Gruber T.R. “A translation Approach to Portable Ontology
Specifications,“ Knowledge Acquisition. Vol.5. pp 199-220, 1993.
[14] Henry M. Kim, “XMLhoo! : A Prototype Application for
Intelligent Query of XML Documents using Domain-Specific Ontologies”, Proceedings of the 35th Hawaii International Conference on System Science, 2002
[15] Latifur Khan, Dennis McLeod, Eduard Hovy, “Retrieval
effectiveness of an ontology-based model for information selection.” The VLDB Journal , pp 71–85, 2004.
[16] Zhenyu Liu, and Wesley W.Chu, “Knowledge-Based Query
Expansion to Support Scenario-Specific Retrieval of Medical Free Text” Proceedings of the 2005 ACM symposium on Applied computing, pp 1076-1083, 2005.
[17] Maron, M. E., and Kuhns, J. L. “On relevance, probabilistic
indexing and retrieval.” J. ACM, Vol.7, pp 216–244, 1960.
[18] WordNet( a lexical database for the English language)
http://www.cogsci.princeton.edu/~wn/
[19] R. Baeza-Yates and B. Ribeiro-Neto, “Modern Information
Retrieval.”, ACM Press, New York, Addison-Wesley, 1999.
[20] Y. Qiu and H.P. Frei. “Concept-based Query Expansion.” In
Proceedings of ACM SIGIR pp 160-169, 1993
[21] J. Xu and W.B. Croft. “Query expansion using local and global
document analysis.” In Proceedings of ACM SIGIR pp 4-11, 1996.
[22] Mitra, A. Singhal, and C. Buckley. “Improving automatic query
expansion.” In Proceedings of ACM SIGIR pp.206-214, 1998.
[23] Miller, W. L."A probabilistic search strategy for MEDLARS."
pp 254–266, Doc. 27, 1971.
[24] http://www.w3.org/TR/2004/REC-owl-features-20040210/
[25] G.Salton, “The Smart Retrieval System – Experiments in
Automatic Document Processing.” NJ: Prentice Hall, Englewood Cliffs, pp 313-323, 1971
[26] Y. Arens, C.N. Hsu, and C. A. Knoblock, “Query processing
in the Sims Information mediator”, Advanced Planning Technology, AAAI Press, California, USA, pp 82-90, 1997.