跳到主要內容

臺灣博碩士論文加值系統

(18.204.48.69) 您好!臺灣時間:2021/07/27 22:41
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:阮忠誠
研究生(外文):Trung Thanh Nguyen
論文名稱:工程知識管理系統中本體論為基之知識淬取工具
論文名稱(外文):Ontology-Based Knowledge Extraction Tool for Engineering Knowledge Management Systems
指導教授:何正得何正得引用關係
指導教授(外文):Chengter Ted Ho
學位類別:碩士
校院名稱:國立高雄應用科技大學
系所名稱:工業工程與管理系碩士班
學門:工程學門
學類:工業工程學類
論文種類:學術論文
論文出版年:2007
畢業學年度:95
語文別:中文
論文頁數:58
中文關鍵詞:工程知識管理本體論知識淬取工具
外文關鍵詞:OntologyOntology-Based Knowledge ExtractionNatural Language Processing
相關次數:
  • 被引用被引用:0
  • 點閱點閱:180
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
本論文是關於開發一個以本體論為基的自動知識淬取工具,一些關於工程領域的資料會由非結構化的工程文件中淬取出,資料經過處理後,而成為知識。本研究使用的方法跟其他研究的方法不同,本知識淬取工具是用本體論模式,以特定領域專家的觀點來淬取資料。而且此本體論模式是以專家領域來建立,其運作方式像是一個過濾器,能將資料從一個非結構化工程文件中的一串文字裡,將資料淬取出來,跟其他方法比較起來,此種方法將能更快、更有效率的淬取相關領域的資料,然後將資料處理後,轉變為欲獲得的知識。 為了達到此目的,一些自然語言處理工具與工程領域的字典提供了語義的注釋。經由比對語義釋與本體論模式中的觀念與屬性後,將能萃取到需求的資料。處理前的本體論與處理後的本體論不同的地方是前者提供了一個藍圖來塑造特定領域的知識,後者是以進行案例式推理與處理來獲得欲取得的知識處理。在本論文中, TFT-LCD 顯示器領域的知識為示範,展示本體論為基之知識淬取工具可以幫助工程知識管理系統完成任務。
The objective of this thesis is to develop an automatic Ontology-based knowledge extraction tool in which data related to an engineering domain will be extracted from the unstructured engineering documents and then processed to acquire expected knowledge. Different from the other approach, this tool allows the knowledge to be extracted from the view point of an expert of the domain by using an Ontology model, which is constructed by an expert of domain, working as a ‘filter’ to extract data from ‘the flow of words’ on a given unstructured engineering document. By following this way, data will be processed with respect to domain knowledge faster and more efficiently than other approach and then processed to acquire desired knowledge. To do so, some natural language processing tools and a dictionary of an engineering domain
are invoked to provide semantic annotation for a given unstructured document. By matching the obtained semantic annotations with the concepts and properties in the Ontology model, the desired data will be extracted to support populating Ontology. The difference between the Ontology before and after populating is that the first provides a
blueprint to model the domain knowledge and the later allows one to acquire expected knowledge by doing reasoning and processing. In this paper, knowledge and domain of TFT-LCD display is selected as a target and object, from which an Ontology-Based Knowledge Extraction tool is built up to help an Engineering Knowledge Management System carry out its task.
TABLE OF CONTENTS
Page
ENGLISH ABSTRACT i
CHINESE ABSTRACT iii
ACKNOWLEDGEMENT iv
TABLE OF CONTENTS v
LIST OF TABLES viii
LIST OF FIGURES ix
CHAPTER
CHAPTER 1: INTRODUCTION 1
1.1 Research background and motivations 1
1.2 Technologies and tools involvements 5
1.3 Structure of thesis 5
CHAPTER 2: LITERATURE REVIEW 7
2.1 Basic terminologies and their definitions 7
2.2 Ontology 9
2.2.1 Ontology Languages 9
2.2.2 Components of OWL Ontology 10
2.2.3 Protégé – an Ontology Editor tool 11
2.3 Semantic Web Rule Language 13
2.4 Natural Language Processing 14
2.5 Information Extraction 16
2.5.1 GATE: an Information Extraction Tool 16
2.5.1.1 Annotation 17
vi
2.5.1.2 Java Annotation Patterns Engine 18
2.5.1.3 SUPPLE (parser) 23
2.6 Related Work 23
CHAPTER 3: METHODOLOGY 28
3.1 OBKE tool support Knowledge Sharing 28
3.2 OBKE tool support Knowledge Capture 29
3.2.1 Capturing Knowledge from experts of domain knowledge 29
3.2.2 Automatic Capture Knowledge from unstructured engineering
documents 31
3.2.2.1 Generating Semantic Annotations 34
3.2.2.2 Matching Semantic Annotations with Ontology 37
3.2.2.3 Populating Ontology 37
3.2.2.4 Application process 38
3.4 OBKE tool support Knowledge Discovery 38
CHAPTER 4: IMPLEMENTATION 39
4.1 Ontology Design 39
4.2 Generating Semantic Annotations 42
4.2.1 Dictionary of Domain Knowledge 42
4.2.2 Token Annotations- Common Information for English Vocabulary43
4.2.3 Parse Annotations-Result of Syntactical Analysis 44
4.2.4 WordNet 45
4.2.5 Semantic Annotations 46
4.3 Matching Ontology classes with Semantic Annotations 48
4.4 Populating Ontology 50
CHAPTER 5: CONCLUSION 54
5.1 Achievements 54
vii
5.2 Limitations 54
5.3 Future works 55
REFERENCES 57
viii
LIST OF TABLES
Page
Table 1: TFT LCD Monitor and their Features 39
ix
LIST OF FIGURES
Figure 1: Three Kinds of Ontology Properties [07] 12
Figure 2: Annotation Graph [16] 18
Figure 3: The Artquakt Architecture [17] 24
Figure 4: An example of knowledge extraction: (a) extraction results and (b) knowledge
triples [17] 25
Figure 5: Automatic Knowledge Capturing System Process 32
Figure 6: Automatic Knowledge Capturing System Architecture 33
Figure 7: ‘Draft’ Ontology - A Graph of Concepts Lattice of TFT-LCD Monitors 40
Figure 8: Ontology for a Group of LCD Monitors 41
Figure 9: OWL Protégé Menu with Classify taxonomy and Check consistency
Ontology Tests [7] 41
Figure 10: Creating Gazetteer Lists to Construct Dictionary of Domain Knowledge 42
Figure 11: Lookup Annotations are created automatically by GATE based on Gazzetter
list 43
Figure 12: Token Annotations and their Features 44
Figure 13: Parse Annotations are created by SUPPLE Parser 45
Figure 14: Parse Tree for a sentence 45
Figure 15: WordNet 1.6 in GATE GUI 46
Figure 16: Create a New Annotation from Token Annotation 47
Figure 17: the Algorithm of Matching Semantic Annotations with Ontology entities 48
Figure 18: Matching Semantic Annotations with Ontology classes and properties 50
Figure 19: Ontology Before and After Populating 52
Figure 20: an example of extracting knowledge from an unstructured document 53
[1] Irma Becerra-Fernandez, Avelino Gonzalez, Rajiv Sabherwal 2004: Knowledge
Management Challenges, Solution, and Technologies. Pearson Prentice Hall Upper
Saddle River, New Jersey, 07458
[2] Ralph Bergmann, Martin Schaaf: Structural Case-Based Reasoning and Ontology-
Based Knowledge Management: A Perfect Match?. Journal of Universal Computer
Science, vol. 9, no. 7 (2003), 608-626
[3] Manago, M., Bergmann, R., Wess, S., Traphöner, R.: CASUEL: A common case
representation language. ESPRIT Project INRECA. Deliverable D1, University of
Kaiserslautern, 1994.
[4] Arcos J., Plaza E.: Reflection in NOOS: An object-oriented representation language
for knowledge modeling. In: IJCAI-95 Workshop on reflection and meta-level
architecture and their applications in AI, 1995.
[5] Leake D. B., Sooriamurthi R.: Automatically Selecting Strategies for Multi-Case-
Base Reasoning. In Proceedings ECCBR 2002: 204-233, 2002.
[6] OWL. http://www.w3.org/TR/owl-features/ (Accessed June 10, 2007)
[7] Matthew Horridge, Holger Knublauch, Alan Rector, Robert Stevens, Chris Wroe: A
Practical Guide To Building OWL Ontologies Using The Protégé-OWL Plugin and COODE
Tools Edition 1.0.
[8] Protégé. http://protege.stanford.edu/ (Accessed June 10, 2007)
[9] RACER. http://www.sts.tu-harburg.de/~r.f.moeller/racer/ (Accessed June 10, 2007)
[10] SWRL. http://protege.cim3.net/cgi-bin/wiki.pl?SWRLLanguageFAQ (Accessed
June 10, 2007)
[11] SWRLTab. http://protege.cim3.net/cgi-bin/wiki.pl?SWRLTab (Accessed June 10,
2007)
[12] Sci-Tech Dictionary definition of natural language processing, McGraw-Hill
Dictionary of Scientific and Technical Terms. http://www.answers.com/topic/naturallanguage-
recognition?cat=technology (Accessed June 10, 2007).
[13] GATE: an Information Extraction tool. http://gate.ac.uk/ie/ (Accessed June 10,
2007)
[14] GATE core team. http://gate.ac.uk/people/index.html/ (Accessed June 10, 2007)
58
[15] Hamish Cunningham, Diana Maynard, Kalina Bontcheva, Valentin Tablan,
Cristian Ursu, Marin Dimitrov, Mike Dowman, Niraj Aswani, Ian Roberts, Yaoyong Li
and Andrey Shafirin: Developing Language Processing Components with GATE
Version 4 (a User Guide). http://gate.ac.uk/sale/tao/index.html (Accessed June 10, 2007)
[16] Valentin Tablan Diana Maynard, Kalina Bontcheva, Hamish Cunningham:
GATE — An Application Developer’s Guide, 19 July 2004.
[17] Harith Alani, Sanghee Kim, David E. Millard, Mark J. Weal,Wendy Hall, Paul H.
Lewis, and Nigel R. Shadbolt: Automatic Ontology-Based Knowledge Extraction from
Web Documents. Published by the IEEE Computer Society January 2003
[18] Fensel D., Decker S., Erdmann M., Studer R.: Ontobroker: The Very High Idea. In:
Proceedings of the 11th International Flairs Conference (FLAIRS-98), Sanibal Island,
Florida, May 1998.
[19] Guarino N., Masolo C., Vetere G.: OntoSeek: Content-Based Access to the Web.
IEEE Intelligent Systems 14(3): 70 – 80.
[20] "formal concept analysis." Wikipedia. Wikipedia, 2007. Answers.com 13 Jul. 2007.
http://www.answers.com/topic/formal-concept-analysis
[21] "WordNet." Data Sources. Answers Corporation, 2006. Answers.com 13 Jul. 2007.
http://www.answers.com/topic/wordnet
[22] Developer Document: GATE API version 4.0. http://www.gate.ac.uk/releases/gate-
4.0-build2752-ALL/doc/javadoc/index.html (Accessed July 23, 2007)
[23] The Concept Explorer. http://conexp.sourceforge.net/ (Accessed June 10, 2007)
[24] Working with WordNet. http://gate.ac.uk/gateexamples/
doc/java2html/sheffield/examples/WordNetApp.java.html (Accessed June 10,
2007)
[25] XML Schema. http://www.w3.org/TR/xmlschema-2/ (Accessed June 10, 2007)
[26] RDF. http://www.w3.org/TR/rdf-primer/ (Accessed June 10, 2007)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top