Muutke küpsiste eelistusi

Multilingual Access and Services for Digital Collections [Pehme köide]

  • Formaat: Paperback / softback, 234 pages, kõrgus x laius: 254x178 mm, kaal: 510 g, 1 Paperback / softback
  • Ilmumisaeg: 18-Jan-2016
  • Kirjastus: Libraries Unlimited Inc
  • ISBN-10: 1440839549
  • ISBN-13: 9781440839542
Teised raamatud teemal:
Multilingual Access and Services for Digital CollectionsSuurem pilt
  • Formaat: Paperback / softback, 234 pages, kõrgus x laius: 254x178 mm, kaal: 510 g, 1 Paperback / softback
  • Ilmumisaeg: 18-Jan-2016
  • Kirjastus: Libraries Unlimited Inc
  • ISBN-10: 1440839549
  • ISBN-13: 9781440839542
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781440839542.html
Märksõnad:
This unique guide offers you a thorough understanding of multilingual information access (MLIA) and services and related concepts, such as database design, information retrieval, machine translation, and natural language processing.

Written for digital library developers, library and information science graduate students, and information professionals serving international information users, this book defines multilingual information access (MLIA) and discusses the importance of enabling international users to access digital collections. Based on a systematic review of the research and development carried out on cross-language information retrieval, machine translation, and case studies of current multilingual digital libraries, the author clearly explains what you need to know about technologies for building MLIA function for digital collections.

The book leads you through an examination of Internet language services and tools that are useful for developing multilingual digital libraries and for assisting international users in accessing digital resources. Content is further clarified by two research projects that are presented to demonstrate the application of technologies used to build MLIA functions and multilingual user interfaces. The book concludes with possible strategies for using Internet language services and tools to implement MLIA function for digital collections.

Muu info

This unique guide offers you a thorough understanding of multilingual information access (MLIA) and services and related concepts, such as database design, information retrieval, machine translation, and natural language processing.
Illustrations xvii
Preface xix
Acknowledgments xxi
Chapter 1 Introduction 1(26)
Digital Information and Information Users
1(2)
Information
1(1)
Digital Information
2(1)
Information Users
2(1)
Digital Libraries and Digital Collections
3(5)
Digital Libraries Defined
3(2)
Digital Libray Architecture
5(1)
Digital Objects
5(1)
Metadata and Metadata Records
6(1)
Digital Collections
7(1)
Services for Digital Collections
8(2)
Searching
8(1)
Browsing
9(1)
Digital Reference Services or Virtual Reference Services
9(1)
Social Media and Interaction
10(1)
World Languages and Linguistics
10(3)
Language
10(1)
World Languages
11(1)
Linguistics-the Discipline of Languages
12(1)
Related Concepts
12(1)
Culture
12(1)
Society
13(1)
Communication
13(1)
Multilingual Information Access
13(5)
Information Access and Its Language Barriers
14(1)
Defining MLIA
15(1)
MLIA for Digital Collections
16(2)
Related Fields
18(5)
Data Modeling and Database Design
18(1)
Full-Text Information Retrieval
19(1)
Natural Language Processing
19(2)
Machine Translation
21(1)
User Studies and User Interfaces
22(1)
Summary and Suggested Readings
23(1)
Questions
24(1)
References
24(3)
Chapter 2 Cross-Language Information Retrieval 27(26)
Information Retrieval and Its Challenges
27(2)
IR Models
29(5)
Boolean Model
30(1)
Vector Space Model
30(1)
Probability Models
31(2)
Google's PageRank Model
33(1)
Cross-Language Information Retrieval
34(5)
CLIR Processes
35(1)
Transformation Strategies
35(2)
Translation Resources and Approaches
37(2)
Dictionaries, Ontologies, and Thesauri
37(1)
Parallel, Comparable, and Combined Monolingual Corpora
38(1)
MT Systems
39(1)
CLIR Translation Problems and Solutions
39(3)
Lexical Ambiguity
40(1)
Untranslatable Search Keys
40(1)
Phrase Identification and Translation
41(1)
Noise in Translation Resources
41(1)
Evaluation
42(3)
Evaluation Methods
42(1)
Evaluation Forums
43(2)
CLIR and MLIR at NTCIR
45(2)
CLIR
45(1)
MLIR
46(1)
Summary and Suggested Readings
47(1)
Questions
48(1)
References
48(5)
Chapter 3 Machine Translation Research and Practice 53(36)
MT and Its History
53(3)
Translation and MT
53(1)
History of MT
54(2)
MT Approaches
56(7)
Rule-Based MT
56(3)
Direct Translation
56(1)
Interlingual Translation
57(1)
Transfer-Based Translation
58(1)
Example-Based MT
59(2)
Statistical MT
61(1)
Hybrid MT Approaches
62(1)
Machine Translation between English and East Asian Languages
63(11)
Characteristics of East Asian Languages
63(3)
Chinese
63(2)
Japanese
65(1)
Korean
66(1)
Chinese and Japanese Text Segmentation
66(7)
n-Gram-Based Text Segmentation
66(1)
Chinese Word Segmentation
67(4)
Dictionary-Based Approaches
68(1)
Statistical and Learning-Based Approaches
69(1)
Hybrid Approaches
70(1)
Use of Chinese Linguistic Knowledge in Word Segmentation
70(1)
Japanese Word Segmentation
71(1)
Word-Based Approaches
72(1)
Character-Based Tagging Approach
72(1)
Evaluation of Word Segmentation
72(1)
MT Systems and Approaches
73(1)
MT Evaluation
74(4)
Overview
75(1)
Human Evaluation Measures
75(1)
Automatic Evaluation Measures
76(1)
MT Evaluation Procedures
76(2)
Data Preparation
76(1)
Determination of Evaluation Measures
77(1)
Reference Translation Creation
77(1)
Evaluator Recruitment
77(1)
Evaluation Platform Development
78(1)
Evaluation Instruction and Progress
78(1)
Result Analysis and Decision Making
78(1)
MT for Information Service
78(3)
MT Applications
79(1)
Use Scenarios in Library and Information Science
80(1)
Summary and Suggested Readings
81(1)
Questions
82(1)
References
83(6)
Chapter 4 Machine Translation for Digital Collections 89(42)
MRT Project: Metadata Records Machine Translation and Evaluation
89(23)
Objectives
90(1)
Research Design
90(1)
Metadata Records Extraction and MT
90(3)
Metadata Records Extraction
90(3)
MT of Selected Records
93(1)
HeMT: The Platform for Human Translation and MT Evaluation
93(10)
HeMT Design Principle
93(1)
Major Functions
94(2)
User Management
94(1)
Multilingual Lexicon Management
94(1)
Manual Translation
95(1)
User Training
95(1)
Evaluation
95(1)
Evaluation Result Visualization
95(1)
Database Design
96(2)
Website Architecture
98(1)
Implementation
98(1)
Usability Testing
99(4)
Workflow
100(1)
Testing Model
101(1)
Pretest and Posttest Questionnaires
102(1)
Test Results and Discussion
103(1)
Evaluation Tasks and Measures
103(3)
Evaluation Tasks
103(1)
Evaluation Measures
104(2)
Evaluator Recruitment and Training
106(2)
The Evaluation Process
108(1)
Results and Analysis
108(2)
Adequacy, Fluency, and the Best System
109(1)
Chinese Translations
109(1)
Spanish Translations
110(1)
Comments from the Evaluators
110(1)
Translation Errors
111(1)
Summary of the Results
111(1)
Building Your Own MT System
112(9)
Procedures for Building an MT System
112(3)
Determining an MT Strategy
112(1)
Selecting an Open-Source MT Platform
113(1)
Analyzing Available Linguistic Resources
113(1)
Installing and Configuring the MT Platform
113(1)
Developing or Purchasing Desired Linguistic Resources
114(1)
Creating an MT System
114(1)
Testing and Adjusting the MT System
114(1)
Documenting the MT System
114(1)
MRT Project: Constructing a Multi-Engine MT System
115(6)
Multi-Engine MT Strategy
115(1)
Moses: The Statistical MT Platform
116(1)
Available Linguistic Resources
117(1)
Moses Installation and Configuration
117(1)
Parallel Corpus Preparation and Monolingual Corpus Acquisition
118(1)
MEMT Strategies and Experimentation
118(1)
Results Analysis
119(1)
Thoughts on Future Improvement
120(1)
Appendix: Data Dictionary for HEMT Database
121(6)
MDR Table
121(1)
MDR-DET Table
122(1)
USER Table
122(1)
REF Table
123(1)
REF-DET Table
123(1)
MT Table
124(1)
MT-DET Table
124(1)
EVAL Table
125(1)
EVAL-DET Table
125(1)
EVAL-COM Table
126(1)
TERM Table
127(1)
Summary and Suggested Readings
127(1)
References
127(4)
Chapter 5 Multilingual Systems and Interfaces 131(26)
Multilingual Digital Libraries and Collections
131(15)
Multilingual Digital Libraries Defined
131(3)
Multilingual Systems on the Internet
131(1)
Multilingual Digital Collections
132(1)
Multilingual Digital Libraries
132(1)
A Framework for Analyzing Multilingual Digital Libraries
133(1)
The Perseus Digital Library
134(3)
Missions & Goals
134(1)
Funding
135(1)
People
135(1)
Organization
135(1)
Services
136(1)
Architecture
136(1)
Technologies
137(1)
The World Digital Library
137(4)
Missions & Goals
137(1)
Funding
138(1)
People
138(1)
Organization
138(1)
Services
139(1)
Architecture
140(1)
Technologies
140(1)
ICDL
141(3)
Missions & Goals
141(1)
Funding
141(1)
People
141(1)
Organization
142(1)
Services
143(1)
Architecture
143(1)
Technologies
144(1)
Characteristics of Multilingual Digital Libraries
144(1)
Challenges and Opportunities to Multilingual Digital Libraries
145(1)
Developing Multilingual Services for Digital Collections
146(8)
General Procedures
146(2)
Planning
146(1)
Analysis
147(1)
Design
147(1)
Implementation
147(1)
User Testing and Modification
148(1)
MLIA Strategies
148(2)
Query Translation-Based
148(1)
Metadata Records Translation-Based
149(1)
Multilingual Interfaces
150(2)
Search Interface
150(1)
Result Display Interface
151(1)
Browsing Interface
152(1)
Related Projects
152(5)
MultiMatch Project
153(1)
MLIA4DC Project
153(1)
Summary and Suggested Readings
154(1)
Questions
155(1)
References
155(2)
Chapter 6 Beyond Retrieval: Knowledge Discovery and Future Directions 157(24)
Knowledge Discovery from Multilingual Texts
157(14)
Multilingual Information Extraction
157(5)
Information Extraction Tasks
158(1)
Entity Identcation and Extraction
158(1)
Scenario or Relationship Detection
158(1)
Event Identification and Extraction
158(1)
General Information Extraction Processes
159(1)
Automatic Metadata Generation
159(1)
Multilingual Information Extraction and Its Challenges
160(2)
Evaluating Multilingual Information Extraction
162(1)
Multilingual Question Answering
162(7)
Introduction
162(1)
Question Analysis
163(2)
Question Answering Approaches
165(1)
Multilingual Question Answering Research
165(3)
NTCIR Multilingual QA Tracks
166(2)
CLEF Multilingual QA Tracks
168(1)
Evaluating Multilingual Question Answering
168(1)
Challenges and Future Development
169(1)
Other Knowledge Discovery Tasks
169(2)
Multilingual Text Summarization
169(1)
Rapid Prototyping of Cross-Language Tools for Low-Resource Languages
170(1)
Cross-lingual Link Discovery
170(1)
Multilingual Social Network Analysis
171(1)
Multilingual Recommender Systems
171(1)
Multilingual News Systems
171(1)
MLIA Challenges and Future Directions
171(2)
Developing and Sharing Knowledge Resources and Tools
172(1)
Integrating Different Approaches
173(1)
Involving Users into the MLIA Procedures
173(1)
Developing and Evaluating Empirical MLIA Systems
173(1)
Preparing For Multilingual Information Access
173(2)
Studying Related Knowledge and Skills
174(1)
Keep an Open Mind to New Technologies
174(1)
Seek Collaboration with MLIA Researchers
174(1)
Summary and Suggested Readings
175(1)
Questions
175(1)
References
176(5)
Chapter 7 Related Internet Language Resources and Tools 181(16)
Dictionaries and Parallel Corpora
181(4)
Monolingual and Multilingual Dictionaries
182(2)
Acronym Finder
182(1)
Dictionaiy.com
182(1)
ADL Gazetteer
182(1)
On-line Chinese Tools
183(1)
Japanese Language Learning Tools on the Web
183(1)
Merriam-Webster Online
183(1)
WordNet
183(1)
Parallel Corpora and Comparative Corpora
184(1)
Canadian Hansards
184(1)
Europarl and JRC-Acquis
184(1)
Chinese-English Parallel Corpora
184(1)
Wikipedia
184(1)
Test Collections
185(1)
TREC Test Collections
185(1)
NTCIR Test Collections
185(1)
Open-Source Systems and Tools
185(6)
Digital Library Management Systems
185(2)
DSpace
186(1)
Fedora
186(1)
Greenstone
186(1)
CONTENTdm
186(1)
Text Processing Systems
187(1)
Apache OpenNLP
187(1)
NLTK
187(1)
Stanford CoreNLP
187(1)
Stemmers
188(1)
Part-of-Speech Taggers
188(1)
Syntactic Parsers
188(1)
Word Segmenters
188(1)
Information Retrieval Systems
188(1)
Lemur & Indri
188(1)
Apache Lucene
189(1)
Terrier
189(1)
Machine Translation Services and Platforms
189(2)
Google Translate
189(1)
Bing Translator
190(1)
SYSTRAN
190(1)
WorldLingo
190(1)
Apertium
190(1)
Moses
190(1)
Joshua
191(1)
NiuTrans
191(1)
Associations and Groups
191(3)
Professional Associations
191(1)
ACM Special Interest Group on Information Retrieval (SIGIR)
191(1)
The Linguistic Society of America
191(1)
The Association for Computational Linguistics
192(1)
Association for Computational Linguistics and Chinese Language Processing
192(1)
Asian Federation of Natural Language Processing (AFNLP)
192(1)
Research Groups
192(1)
Research Groups in Information Retrieval
192(1)
Industrial Research Groups
193(1)
Other Organizations
193(1)
Linguistic Data Consortium (LDC)
193(1)
European Language Resources Association
194(1)
Corpora-List
194(1)
Research and Publication Sites
194(3)
ACL Anthology
194(1)
ACM Digital Library
194(1)
Other Repositories and Archives
195(1)
Dr. Oard's Website
195(1)
MT Archive
195(1)
Statistical MT
195(1)
Publications from Large-Scale Evaluations
195(1)
References
195(2)
Acronym List 197(4)
Glossary 201(4)
Index 205
Jiangping Chen, PhD, is associate professor in the Department of Library and Information Sciences at the University of North Texas (UNT).