文件檢索的技術行之有年，現今已廣泛地運用在各種線上文件檢索系統中。大部份的檢索工具是依據使用者輸入的查詢字串進行全文比對，或者將查詢字串做過部份處理之後再行比對文章。目前，已有為數眾多的研究者致力於發展文章分類、相關文章比對、文件相似度衡量方法及權重計算模型，更有許多改良過的方法實際應用於檢索系統中，逐步改善檢索效果與效率。
於本論文中，我們以現行著名之SCI/SSCI期刊文獻資料庫檢索工具為對象，根據此類文章之特色額外發展文章相似度比對方法。本研究專注於該檢索工具所擁有的標題、摘要、關鍵字及引用文獻，共四項不同特色的重要屬性，並利用著名之向量空間模式和TFIDF公式，計算文章向量的相似度。由於四項屬性之權重大小將影響兩兩文章之整體相似度，我們輔以倒傳遞類神經網路技術，建立屬性權重分配與兩兩文章之間的總相似度值之關係模式。而為了驗證ANN模組之成效，以及本文提出的文章比對方法與傳統比對方法之差異，本論文實際建立真實的期刊文章資料庫，並按照文章比對流程進行研究實作。最後則設計實驗，邀請實驗受測者測試文章比對之效果。
實驗結果顯示，我們所提出的文章比對方法，相較傳統方法而言，確實能大幅改善相似度比對效果。同時，我們也驗證了ANN模組確實帶來更佳的成效。
在SCI/SSCI檢索工具中，本研究期望能在保留標準欄位查詢功能之前提下，額外增加本論文所發展之文章相似度比對方法，藉以提昇檢索工具之彈性及實用性，協助研究學者或一般使用者更有效地查詢資料庫內相關文章。

第一章 緒論 1
第一節 研究背景 1
第二節 研究動機 2
第三節 研究目的 3
第四節 研究流程 4
第五節 論文架構 5
第二章 文獻探討與相關技術 6
第一節 文章前處理 6
第二節 文章比對 12
第三節 相關技術與方法 17
第三章 文章比對方法 24
第一節 文章比對流程概述 24
第二節 文章前處理 26
第三節 建構文章向量及引用文獻列表 29
第四節 處理新文章 41
第五節 文章相似度比對 43
第四章 實證評估 48
第一節 實驗發展工具與環境 48
第二節 建立文章資料庫 50
第三節 實驗設計及實驗流程 51
第四節 評估準則 58
第五節 實驗結果及分析 60
第五章 結論與未來展望 67
第一節 研究結論與貢獻 67
第二節 研究限制 67
第三節 未來展望 69
參考文獻 70
附錄A：STEMMING－PORTER’S ALGORITHM 75

[1]Amer-Yahia, S., Botev, C. and Shanmugasundaram, J., 2004. TeXQuery: A Full-Text Search Extension to XQuery. In Proceedings International WWW Conference, New York, USA.
[2]Amer-Yahia, S., Fern´andez, M., Srivastava, D. and Xu, Y., 2003. Phrase Matching in XML. Proceedings of the 29th VLDB Conference, Berlin, Germany.
[3]Baeza-Yates, R. and Ribeiro-Neto, B., 1999. Modern Information Retrieval. New York: The ACM Press.
[4]Buckley, C., SMART, Version 7.
[5]Callan, J.P., Croft, W.B. and Harding, S.M., 1995. The INQUERY Retrieval System. In DEXA 3. International Conferrence on Database and Expert Systems Applications, pp. 83-97, Berlin: Springer Verlag.
[6]Cohen, W., June 1998. Integration of Heterogeneous databases Without Common Domains Using Queries Based on Textual Similarity. In Proceeding ACM SIGMOD, 27(2): pp. 201-212, Seattle, WA.
[7]CORDIS: Community Research & Development Information Service, http://www.cordis.lu/en/home.html.
[8]Cutting, D. and Pedersen, J., 1990. Optimizations for Dynamic Inverted Index Maintenance. The 13th International Conference on Research and Development in Information Retrieval, pp. 405-411.
[9]Deerwester, S., Dumais, S.T., Furnas, G.W., Landauer, T.K. and Harshman, R., 1990. Indexing by Latent Semantic analysis. Journal of the American Society for Information Sciences, 41, 6, pp. 391-407.
[10]Dickson, G.W., Senn, J.A. and Chervany, N.L., May 1977. Research in Management Information Systems: The Minnesota Experiments. Management Science, vol. 23, no. 9, pp. 913-923.
[11]Doszkocs, T.E., 1983. From Research to Application: The CITE Natural Language Information Retrieval System. In Research and Development in Information Retrieval, Salton, G. and Schneider, H.J., eds. (Lecture Notes in Computer Science Series, 146) Berlin: Springer-Verlag, pp. 251-262.
[12]Dumais, S.T., 1991. Improving the retrieval of information from external sources. Behavior Research Methods, Instruments & Computers, vol. 23, no. 2, pp. 229-236.
[13]Ellman, J., 2000. Using Roget's Thesaurus to Determine the Similarity of Texts. Ph.D. Thesis, School of Computing, Engineering and Technology, University of Sunderland, England.
[14]Fagan, J.L., March 1989. The Effectiveness of a Nonsyntactic Approach to Automatic Phrase Indexing for Document Retrieval. Journal of the American Society for Information Science (ASIS), Vol. 40, Iss. 2, pp. 115-132.
[15]Fellbaum, C., 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, MA.
[16]Fontaine, A., May 1995. Sub-element indexing and probabilistic retrieval in the POSTGRES database system. Technical Report CSD-95-876, University of California at Berkeley. ftp://s2k-ftp.CS.Berkeley. EDU/pub/postgres/papers/.
[17]Fox, C., 1990. A stop list for general text. SIGIR Forum 20(12), pp. 19-35.
[18]Frakes, W.B. and Fox, C.J., 2003. Strength and similarity of affix removal stemming algorithms. SIGIR Forum 37(1): pp. 26-30.
[19]Geffet, M. and Feitelson, D.G., Jun 2001. Hierarchical indexing and document matching in BoW. In first ACM/IEEE Joint Conferrence Digital Libraries, pp. 259-267.
[20]George Allan Alderman III, M.A., 2000. Information Retrieval using an adaptive resonance theory (ART)-based Neural Net. Ph.D. dissertation, Georgetown University, UMI Number: 9978116.
[21]Grossman, D.A. and Frieder O., 1998. Information Retrieval: algorithms and heuristics. Boston: Kluwer.
[22]Hammouda, K. and Kamel, M., 2004. Document Similarity Using a Phrase Indexing Graph Model. Knowledge and Information Systems, vol. 6, no. 6, pp. 710-727.
[23]ISI Web of Knowledge, Version 3.0, http://isi01.isiknowledge.com/portal.cgi.
[24]Korfhage, R.R., 1997. Information Storage and Retrieval. N.Y.: John Wiley and Sons.
[25]Kowalski, G.J. and Maybury, M.T., 2000. Information Storage and Retrieval Systems: Theory and Implementation. Kluwer International Series on Information Retrieval, Inre 8. Kluwer Academic.
[26]Lee, K.H., Choy, Y.C. and Cho, S.B., 2004. An Efficient Algorithm to Compute Differences between Structured Documents. IEEE Transactions on Knowledge and Data Engineering, 16(8): pp. 965-979.
[27]Lin, D., 1997. Using Syntactic Dependency as Local Context to Resolve Word-Sense Ambiguity. In Proceedings of the Thirty-Fifth Annual Meeting of the Association for Computational Linguistics. Somerset, N.J.: Association for Computational Linguistics.
[28]Lin, S.H., Shih, C.S., Chen, M.C., Ho, J.M., Ko, M.T. and Huang, Y.M., 1998. Extracting Classification Knowledge of Internet Documents with Mining Term Associations: A Semantic Approach. SIGIR: pp. 241-249.
[29]Luhn, H.P., 1958. The automatic creation of literature abstracts. IBM Journal of Research, 2(4): pp. 159-165.
[30]Maayan, G. and Feitelson, D., 2001. Hierarchical Indexing and Document Matching in BoW. Proceedings of the first ACM/IEEE-CS joint conference on Digital Libraries, Roanoke, Virginia, pp. 259-267.
[31]Meadow, C.T., Wang, J. and Stamboulie, M., 1993. An Analysis of Zipf-Mandelbrot Language Measures and Their Application to Artificial Languages. Journal of Information Science, 19(4): pp. 247-258.
[32]Meadow, C.T., Boyce, B.R., and Kraft, D.H., 2000. Text Information Retrieval Systems. 2nd edition. San Diego: Academic Press.
[33]Michaelj, A.B., 1997. Data Mining Techniques For Marketing, sales, and Customer Support. Wiley Computer Publishing.
[34]Miller, G., Beckwith, R., Fellbaum, C., Gross, D. and Miller, K., 1990. Introduction to WordNet: An on-line lexical database. J. Lexicography 3(4): pp. 235-244.
[35]Miller, G.A., 1995. WorldNet: a lexical database for English. Communications of the ACM, 38(11): pp. 39-41.
[36]Ng, H.T. and Zelle, J., 1997. Corpus based approaches to semantic interpretation in natural language processing. AI Magazine, 18(4): pp. 25-31.
[37]Palo Alto, C.A., 1987. Dialog Information Services. DIALOG System Seminar Manual, Problem Set 3.1.1, pp. 20.
[38]Patel-Schneider, P.F., Simeon, J., 2003. The Yin/Yang Web: A unified model for XML syntax and RDF semantics. IEEE Transactions on Knowledge and Data Engineering, 15: pp. 797-812.
[39]Petrakis, E.G.M. and Tzeras K., November 2000. Similarity Searching in the CORDIS Text Database. Software Practice and Experience, Vol. 30, No. 13, pp. 1447-1464.
[40]Principe, C.J., Euliano, R.N. and Lefebvre, W.C., 2000. Neural and Adaptive Systems: Fundamentals Through Simulations. John Wiley and Sons.
[41]Quah, T.S. and Srinivasan B., 2000. Utilizing Neural Networks in Stock Pickings. Proceedings of the International Conference on Artificial Intelligence.
[42]Raeisi, R., 2005. Modeling and Verification of Digital Logic Circuit Using Neural Networks. 2005 ASEE IL/IN Sectional Conference, Session B-T2-3.
[43]Rijsbergen, C.J., 1975. Information Retrieval. Butterworth.
[44]Salton, G. and Yang, C.S., 1973. On the Specification of Term Values in Automatic Indexing. J. Documentation 29(4), pp. 351-72.
[45]Salton, G. and McGill, M.J., 1983. Text Analysis and Automatic Indexing in Introduction to Modern Information Retrieval. New York: McGrae-Hill.
[46]Salton, G., July 1986. Another Look At Automatic Text Retrieval Systems. Communication of the ACM, vol. 29, no. 7, pp. 648-656.
[47]Salton, G. (editor), 1988. Automatic Text Processing: The Transformation, Analysis and Retrieval of Information by Computer. Addison Wesley.
[48]Salton, G. and Buckley, C., 1988. Improving retrieval performance by relevance feedback. Computer Science Technical Report TR88-898, Department of Computer Science, Cornell University, Ithaca, N.Y.
[49]Salton, G., 1989. Automatic Text Processing. Addison-Wesley.
[50]Weiss, S.M., White, B.F., Apte, C.V. and Damerau, F.J., March 2000. Lightweight Document Matching for Help-Desk Applications. IEEE Intelligent Systems, vol. 15, no. 2, pp. 57-61.
[51]Spark Jones, K. and Furnas, G.W., November 1987. Pictures of relevance: A geometric analysis of similarity measures. Journal of the American Society for Information Science, 38(6): pp. 420-442.
[52]Suarez, A., Noeda, M. and Palomar, M., 1999. A Method of Restricted Knowledge Acquisition from WordNet. Proceeding of the third International Conference on Knowledge-Based Intelligent Information Engineering System, IEEE, pp. 38-41.
[53]Turban E. and Aronson J.E., 2001. Decision Support Systems and Intelligent Systems. sixth edition, Prentice Hall.
[54]Tzeras, K. and Petrakis, E.G.M., 1999. Similarity searching in text databases with multiple field types. Proceedings, the fifteenth International Conference on Data Engineering, pp. 100.
[55]Utsuro, T., Ikeda, H., Yamane, M., Matsumoto, Y. and Nagao, M., 1994. Bilingual Text Matching using Bilingual Dictionary and Statistics. Proceedings of fifteenth International Conference on Computational Linguistics, pp. 1076-1082, Kyoto.
[56]Wei, J., Bressan, S. and Ooi, B.C., 2000. Mining Term Association Rules for Automatic Global Query Expansion: Methodology and Preliminary Results. Proceedings of the First International Conference on Web Information Systems Engineering, pp. 366-373.
[57]Web WordNet, Version 2.0, http://wordnet.princeton.edu/cgi-bin/webwn.
[58]Yarowsky, D., 1995. Unsupervised Word Sense Disambiguation rivaling Supervised Method. Proceedings of the Thirty-third Annual Meeting of the Association for Computational Linguistics, pp. 189-196.
[59]Yunjae Jung, Haesun Park and Ding-zhu Du, 2001. A Balanced Term-Weighting Scheme for Effective Document Matching. Technical Report TR-01-009, Department for Mathematics and Computer Science, University of Mannheim.
[60]Zipf, G.K., 1949. Human Behavior and the Principle of Least Effort. Addison-Wesley. Cambridge, MA, pp. 22-27.