摘要
自然語言的溝通方式與人類的生活上有密不可分的關係，因此本論文就發展以自然語言來查詢在資料庫中的資訊，利用具有模糊比對的觀念比對法，將使用者所輸入的中文查詢語句轉換成SQL，讓使用者在不瞭解資料庫結構綱要和不需瞭解資料庫查詢操作的狀況下，提供使用者一具有彈性和有效率的智慧型資訊查詢系統，以類似人與人溝通的對話方式，對資料庫系統查詢其需求，而達到資訊便利共享的目的。本研究以資料關鍵詞典的建立和LCS(longest common subsequence algorithm)最長相同子字串模糊比對為基礎，從自然語言擷取關鍵詞，經過適當的語意分析並轉換成SQL模式，主要包含了三大模組─中文關鍵詞擷取、語意分析及SQL轉換處理。目前已獲致初步的實驗成果。

Abstract
This paper aims at transforming Chinese natural language queries into SQL commands to provide an intelligent query system with a human-machine dialogue interface. The system is composed of three modules: Chinese keywords fuzzy extraction, semantic analysis, and SQL transformation. The first module is based on LCS (longest common subsequence algorithm) that supports fuzzy matching. The second module decides semantic frames from semantic lexicon, which is generated from a database beforehand. Finally, rules are used to convert the semantic frames into SQL. In the end, we have achieved initial experimental results to supply a flexible, convenient and efficient method for users to query actual data they want from database.

Table of Contents
ABSTRACT (In Chinese) ……………………………………………………………v
ABSTRACT (In English) ……………………………………………………………vi
ACKNOWLEDGEMENTS (In Chinese)……………………………...……………vii
TABLE OF CONTENTS .……………..…………………………….……………viii
LIST OF FIGURES .………………………………………………………………ix
LIST OF TABLES ...……...…………………………………………………………x
CHAPTER 1 INTRODUCTION ...…………………………………………………1
1.1 Background and Motivation………………………………………………………1
1.2 Objectives and Methods…………………………...………………………………4
1.3 Chinese Natural Language Transformation Processing……………………………6
1.3.1 Clause Boundary Identification & Word Segmentation…...…………………….7
1.3.2 Semantic Analysis and SQL transformation…...………………………………..8
CHAPTER 2 Background Knowledge……………………………………………11
2.1 Chinese String Manipulation Procedure. ………………………………………..11
2.2 Natural language processing…………………………………………………..…15
2.3 Sentence & Semantic Parsing……………………………………………………18
CHAPTER 3 Chinese Natural Language Query Transforming into SQL
Application ……………………………………………………………21
3.1 How to construct the semantic lexicon…………………………….…………….25
3.2 Methodology………………………………………….………………………….26
3.3 keywords matching module…………………………….………………………..35
3.4 Fault-Tolerance (keyword fuzzy matching use in LCS)……………….…………38
3.5 Semantic frames analysis…………………………………………….…………..41
3.6 The intention of Query inferred and SQL transformation………………..………44
CHAPTER 4 Experimental Analysis……………………………….……………..49
4.1 Experimental Results………………………………………………………………49
4.2 Results Analysis……………………………………………………………………50
CHAPTER 5 Conclusion and future direction……….…………………………….52
5.1 Future Works……………………………………………...……………………….53
REFENCES ...….………………………………………….……………………..…55
LIST OF FIGURES
Figure1-1 Natural language Based Information Query Structure……………………..6
Figure1-2 The Framework of a Natural Language Processing System………….…….7
Figure2-1 The structure of ANI (The proposed framework of ANI system)………....14
Figure2-2 the relationship of the three components of ANI………………………….15
Figure 2-3 The structure of the OPTM…………………………………….……….…16
Figure 2-4 (a) Semantic Role in a sentence (b) Mapping the Semantic Role into realistic situation……………………………………..…………………………..…17
Figure 3-1 CNLTS………………………………………..…………………………..22
Figure 3-2 The equivalence algorithm………………………………………..………31
Figure 3-3 Item & value are represent the database structure…………….…………..32
Figure 3-4 SQL Transformation Reasoner……………………………………………46
LIST OF TABLES
Table 3-1: The structure of the semantic lexicon……………………..…………….28
Table 3-2: The Boolean logical semantic lexicon………………………….……….29
Table 3-3: Regular expressions………………………………………………………29
Table 3-4: Matching Results………………………………………………………….37
Table 3-5 LCS Analysis……………………………………………………………....40
Table 4-1 Experimental Results Ⅰ……………………………………….………….49
Table 4-2 Experimental Results Ⅱ……………………………………..……………50
Appendix A…….…………..………………………………………………………..61
Appendix B…………………………………………………………………………62

References
[1] Ana Paula Ambrosio, Elisabeth Métais, and Jean-Noël Meunier (1997), “The linguistic level: Contribution for conceptual design, view integration, reuse and documentation,” Data and Knowledge Engineering, 21 (2), pp. 111-129.
[2] Elisabeth Métais (2002), “Enhancing information systems management with
natural language processing technique,” Data and Knowledge Engineering, 41 (2), pp.247-272.
[3]. Lee-Feng Chien, K. J. Chen and L. S. Lee (1991), “A Preference-first Language Processor Integrating the Unification Grammar and Markov Language Model for Speech Recognition Applications.” Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, (ACL''91),Jun 1991, Berkley, CA, USA.
[4] Lee-Feng Chien, K. J. Chen and L. S. Lee (1991), “Augmented Chart Data Structure with Efficient Word Lattice Parsing Scheme in Speech Recognition Applications.” Speech Communication, Vol. 10, No. 2, Apr 1991.
[5] Lee-Feng Chien, K. J. Chen and L. S Lee (1993), “A Best-first Language Processing Model Integrating the Unification Grammar and Markov Language Model for Speech Recognition Applications.” IEEE Trans. On Speech and Audio Processing, Vol. 1, No. 2, Apr 1993.
[6] Lin-Shan Lee, Lee-Feng Chien, Long Ji Lin, James Huang, Keh-Jiann Chen (1991), “An Efficient Natural Language Processing System Specially Designed for the Chinese Language.” Computational Linguistics, Dec. 1991, 17(4), pp. 347-373.
[7]陳景堂、民80，自然語言查詢系統新架構，私立淡江大學管理科學研究所博士論文 CHEN, JIAN-TANG A new framework of natural language query system
[8] Frank S.C Tseng, A.L.P. Chen, and W.-P.Yang(1991), ”Extending the E-R concepts to capture natural language semantics for database access,” Computer Software and Applications Conference, 1991. COMPSAC ''91., Proceedings of the
Fifteenth Annual International, pp. 30—35.
[9] Frank S.C Tseng, Arbee L.P Chen, and Wei-Pang Yang (1992), “On mapping 392
natural language constructs into relational algebra through E-R representation,”
Data and Knowledge Engineering, pp. 97-118.
[10] P.H Winston (1984), Artificial Intelligence, Addison-Wesley.
[11]曾守正與陳淳齡(2002)民91，『透過 UML 表示法將自然語言查詢轉換成 SQL之研究』，第八屆資訊管理研究暨實務研討會論文集，國立高雄第一科技大學主辦，第385 頁 ~ 392 頁。
[12] Judith S. Brown, Sandra L. Emerson & Marcy Darnovsky “Programming Bile Series SQL Bible” Addison Wesley, 1993.
[13] Moshé Zloof of IBM(1975). “A user-friendly query language”
[14] Moshé M. Zloof(1975), "Query By Example", AFIPS NCC 1975: 431-438
[15] Moshé M. Zloof(1977), "Query-by-Example: A Data Base Language", IBM Systems Journal 16(4): 324-343.
[16] M.M. Zloof (1981) "QBE/OBE: A Language for Office and Business Automation", Computer pp.13-22, May.
[17] J Cooke, S Gregor, J Luck, JL Clark, KT Lua, J McCallum, "Analyzing the conformance of Chinese text to Zipf''s law and Automatic indexing of natural language text in the UNIX environment", (transcript of slides, 1996? Univ of Central Queensland, Australia)
[18] R Rousseau, Qiaoqiao Zhang (1992), "Zipf''s data on the frequency of Chinese words revisited", Scientometrics, 24(2):201-220.
[19] 陳克健,陳正佳,林隆基 (1986) 中文語句分析研究-斷詞與構詞 中央研究院資訊所1986技術報告
[20] K.J. Chen and S.H Liu (1992) “word Identification for Mandarin Chinese Sentences,” Proceedings of 14th International Conference on Computational Linguistic,1992 , pp.101-107.
[21] J.S. Chang, Z.D. Chen and S.D. Chen (1991) “A Method of Word Identification for Chinese by Constraint Satisfaction and Statistical Optimization Techniques, “Proceeding of ROCLING, 1991, pp. 147-165.
[22] J.S. Chang, et al. (1994) “A Multiple-Corpus Approach to Recognition of Proper Names in Chinese Texts, “Computer Processing of Chinese and Oriental Languages, Vol.8, No.1, 1994, pp. 75-85.
[23] H.H. Chen, K.H. Chen and Y.S. Lee (1994) “A Corpus-Based Language Model for Topic Identification,” Bulletin of the College of Engineering, National Taiwan University, No.62, 1994, pp. 97-106.
[24] M.S. Sun, D. Shen and C. Huang (1997) “Cseg&Tag1.0: A Practical Word Segmenter and POS Tagger for Chinese Texts, “Proceedings of Applied Natural Language Processing, 1997, pp. 119-126.
[25] G. Brown and G. Yule (1983) Discourse Analysis, Cambridge, Cambridge University Press,1983.
[26] D. Crystal (1980) “Neglected Grammatical Factors in Conversational English,” S. Greenbaum, G. Leech and J. S vartvik, editor, Studies in English Linguistics, Longman, 1980.
[27] W.J.M Levelt (1983) “Monitoring and Self-Repair in Speech,” Cognition, Vol. 14, 1983, pp.41-104.
[28] Yue-Shi Lee (1997) “New Approaches to Corpus-Based Chinese Spoken Language Processing” Doctor Thesis Department of C.S.&I.E. , National Taiwan University.
[29] M.S. Shaw (1996) Design and Implementation of a Treebank Development Tool, Master Thesis, Department of Computer Science and Information Engineering, National Taiwan University.
[30] Robert F.Simmons (1970) “Natural Language Question-Answering Systems” Communication of the ACM, VOL 13, No. 1, January,1970 pp.15-30.
[31] D. S. I Iirschbcrg (1977) “Algorithms for the longest common subsequence problem, J.ACM 24(4) pp.664-675.
[32] Eugene Charniak (1993) “Statistical Language Learning”, A Bradford Book The MIT press Cambridge, Massachusetts London, England.
[33] ELLIS HOROWITZ, SARTAJ SAHNI, and DINESH MEHTA “Fundamentals Of Data Structures in C++” 余建政,謝志明編譯 松崗電腦圖書資料股份有限公司出版.
[34] C.K. Fan and W.H. Tsai (1988) “Automatic Word Identification in Chinese Sentences by the Relaxation Technique,” Computer Processing of Chinese and Oriental Language, Vol.4, No.1, 1988, pp. 33-56.
[35] J.S. Chang, Z.D. Chen and S.D. Chen (1991) “A Method of Word Identification for Chinese by Constraint Satisfaction and Statistical Optimization Techniques,” Proceedings of ROCLING, 1991, pp. 147-165.
[36] K.J. Chen and S.H. Liu (1992) “Word Identification for Mandarin Chinese Sentences,” Proceedings of 14th International Conference on Computational linguistics,1992, pp. 101-107.
[36] R. Sproat, et al. (1994) “A stochastic Finite-State Word-Segmentation Algorithm for Chinese,” Proceedings of 34th Annual Meeting of ACL,1994 , pp. 66-73.
[37] H.H. Chen and J.C. Lee (1996) “Identification and Classification of Proper Nouns in Chinese Texts,” Proceedings of 16th International Conference on Computational Linguistics,1996 , pp.222-229.
[38] M.S. Sun, D. Shen and C. Huang (1997) “Cseg&Tag1.0: A Practical Word Segmenter and POS Tagger for Chinese Texts,” Proceedings of Applied Natural Language Processing,1997, pp. 119-126.
[39] Judith S. Bowman, Sandra L. Emerson, Marcy Darnovsky “The practical SQL Handbook SQL Bible Using Structured Query Language” 鄭曉強、丁世杰 譯 艾迪生維斯理朗文出版有限公司 1997
[40] Lee Kuen-Lin “Intention Extraction and Semantic Matching for Internet FAQ Retrieval”
[41] Yun Cho Huang (1999)“A Study on Natural Language Processing for a Bank Telephone Service System”, Master Thesis Department of Applied Math, National Chung-Hsing university(1999).