臺灣博碩士論文加值系統

本論文主旨在設計以正規文句為主的文件資訊萃取系統。此設計是利用正規定義及領域屬性特質，配合關聯式資料模型，完成資訊萃取。目的在改善半結構文件查詢、管理上先天性的弱點，此模型的特點是能在異質的領域內依需求做不同的資訊萃取。
基於半結構化文件和中文語法的特性，文中提出將半結構文件內容轉換成資料庫表格的方法論及實驗證明，另外比較在完成正規化後查詢路徑的變化及查詢能力的改善。本研究以資訊應用的角度來思考文件處理的問題，分析傳統表格型態涵蓋半結構文件資訊的能力，進而發展電子文件寫作的新標準，提高文件的被查詢能力及降低加值處理的困難。

The objective of this paper is to design an information extraction system, which focus on sentences with normal forms. This system executes the information extraction by using normalized definitions, the properties of domain attributes and the relative data models. The purpose of this paper is to improve the functions of query semi-structured documents and to reduce the defects in management. The feature of this model can extract information from the different style document by user’s demand.
This extraction system is based on the characteristics of semi-structured documents and Chinese grammars. We submit a methodology to describe how to transfer semi-structured documents into database and prove the methodology by experiments. Besides, we evaluated the differences of query path after normalization and assessed the performance of query ability.
This research reflects on documents processing in view of information applications. It analyses the capability of covering semi-structured documents into a traditional table and further, it develops the standards for documents writing to enhance the capability of documents being queried and reduce the difficulty of add-value processing.

摘要 i
ABSTRACT ii
目錄 iii
圖目錄 v
一 序論 1
1.1 背景說明 1
1.2 研究目的及動機: 2
1.3 研究方法及步驟 6
1.4 論文架構 8
二 相關文獻及技術研究 9
2.1 相關技術 9
2.1.1 中文斷詞 9
2.1.2 詞性標示 13
2.1.3 關鍵字擷取 13
2.2 Multigraph資料模式 14
2.3 文件庫系統簡介 16
2.3.1 TDM系統 16
2.3.2 P-Strings模式 18
2.3.3 PAT系統 19
2.3.4 TOMS系統 22
2.3.5 The containment 模式 23
三 文件資訊擷取系統分析 25
3.1 文件資料庫的設計 25
3.1.1 資料庫設計的需求 25
3.1.2 實體關係圖形模式 26
3.2 正規化的定義 28
3.2.1 字詞層的正規化 (Term Level Normalization) 28
3.2.2 標準文句的概念及應用 30
3.2.3 文句層的文件規格化 31
四 系統架構 36
4.1 前置工作 37
4.1.1 建立分類的字詞庫 37
4.1.2 文件之樹狀結構剖析參考 37
4.1.3 領域型態的分析 38
4.2 文件處理程序 39
4.2.1 去除冗餘資訊 39
4.2.2 斷詞及斷句的處理 41
4.2.3 正規化的處理及資訊萃取 42
4.3 系統參數調整 45
五 系統成果評估 46
5.1 查詢的應用 46
5.2 評估參數 49
5.3 實驗結果分析 51
六 結論及未來發展方向 58
6.1 結論 58
6.2 未來研究發展的方向 58
參考文獻 60

[1] Augusto Celentan , et al., “Knowledge-Based Document Retrieval in Office Environment: The Kabiria System”, ACM Tranacations of Information Systems, Vol.13, NO.3 Pages 237-268 , July 1995
[2] V.Christophides,et al., “From Structured Documents to Novel Query Facilities”,SIGMOD,94-5/94 Minneapoils,Minnestoa, USA,Pages 313-324,1994
[3] 何文雄；1983，中文斷詞的研究，國立台灣工業技術學院碩士論文
[4] Chen,K.J et al .Word Identification for Mandarin Chinese Sentences, Proceedings of COLING-92 ,14 th Int. conference on Computational Linguistics ,pp. 101-107,July 23-28,1992
[5] [10]C.K.Fan and W.H.Tsaai,1987,Automatic Word Identification in Chinese Sentence by the Relaxation Technique ,Proc. of National Computer Symposium,pp423-431,National Taiwan University ,Taipei ,Taiwan
[6] Lee ,H.J et al. Rule-Based Word Identification for Mandarin Chinese Sentences —A unification Approach . Computer Processing of Chinese and Oriental Languages . Vol5 ,no 2,pp.970118,March 1991
[7] Richard Sproat and Chilin Shih,1990,A Statistical Method for Finding Word Boundaries in Chinese Text, Computer Processing of Chinese & Oriental Langages,Vol4,March 1990
[8] 彭載衍，”中文辭彙岐義之解決-斷詞與詞性標示”，國立清華大學碩士論文，1993
[9] Burgin,R,,Dillon,M” Improving Diaambiguation in FASIT ,”Journal of American Society for Information Scinece,43920,1992,101-114
[10] FanganmJ,L,”The Effectiveness of a Nonsyntatic Approach to Automatic Phrase Indexing for Document Retrieval,” Journal of American society for Information Science ,40(2),1989,115-132
[11] Zimin Wu and Gwyneth Tseng,”ACTS: An Automatic Chinese Text Segmentation System for Full Text Retrieval . ”Journal of American Society for Information Scince,46(2),1995,83-96
[12] Travis.Waldt, The SGML Implementation Guide, Springer-Verlag,1995
[13] Eric Van Herwijen. Practical SGML. Kluwer Academic Publishers Group, Dordrecht ,The netherlands,1990
[14] ISO 8879:1986,Information Processing Text and Office Systems Standard Generalized Markup Language, 1986
[15] 中研院中文詞知識庫小組，技術報告93-03 新聞常用動詞詞頻分析
[16] 中研院文詞知識庫小組，技術報告93-05 中文詞類分析
[17] 陳淑美，財經新聞自動分類之研究，(碩士論文)，臺灣大學，1992
[18] Peter Buneman、Susan Davidson、Mary Fernandez、Dan Suciu，Adding Structure to Unstructured Data，University of Pennsylvania，1997
[19] Peter Buneman、Susan Davidson、Dan Suciu，Programming Constructs for Unstructured Data 、University of Pennsylvania，1997
[20] Koichi Munakata，Integration of Semistructured Data Using Outer Joins，Industrial Electronics & Systems Laboratory, 1997
[21] Jason Mchugh、Jennifer Widom，Integrating Dynamically-Fetched External Information into DBMS for Semistructured Data，Department of Computer Science Standford University，1997
[22] Robert A. Nado、Scott B. Huffman，Extracting Entity Profiles from Semistructured Information Spaces，Price Waterhouse Technology Centre，1997
[23] Serge Abiteboul 、Roy Goldman、Jason McHugh、Vasilis Vassalos、Yue Zhuge，Views for Semistructured data，Department of Computer Science Standford University 1997
[24] Dan Smith、Mauricio Lopez，Information Extraction for Semistructured Documents，GIE Dyade，INRIA Ehone-Alpes，1997
[25] Vipul Kashyap、Marek Rusinkiewicz，Modeling and Query Textual Data Using E-R Models and SQL，Microelectronics and Computer Technology Corporation，1997
[26] Peter Buneman、Susan Davidson、Gerd Hillebrand，A Query Language and Optimization Techniques for Unstructured Data，AT&T Research，1997
[27] Mary Fernandez、Daniela Florescu、Alon evy、Dan Suciu，A Query Language and Processor for Web-Site Management System ，AT&T Research，1997