[工学]跨语言资讯检索导论

《[工学]跨语言资讯检索导论》由会员上传分享，免费在线阅读，更多相关内容在教育资源-天天文库。

1、跨語言資訊檢索導論Hsin-HsiChen(陳信希)DepartmentofComputerScienceandInformationEngineeringNationalTaiwanUniversityHsin-HsiChen1OutlineMultilingualEnvironmentsWhatisCross-LanguageInformationRetrieval?MajorProblemsinCLIRMajorApproachesinCLIRCaseStudy:CLIRinNPDMSummaryHsin-HsiChen2MultilingualCollectionsTherea

2、re6,703languageslistedintheEthnologueDigitallibrariesOCLCOnlineComputerLibraryCenterservesmorethan17,000librariesin52countriesandcontainsover30millionbibliographicrecordswithover500millionrecordsownershipattachedinmorethan370languagesWorldWideWebAround40%ofInternetusersdonotspeakEnglish,however,

3、80%ofWebsitesarestillinEnglishHsin-HsiChen3真實世界語言使用人口(http://www.g11n.com/faq.htm)中文英語印度語西班牙語葡萄牙語孟加拉語俄語阿拉伯語日語Hsin-HsiChen4(StatisticsfromEuro-MarketingAssociates,1998)西班牙語德語日語法語中文荷蘭語葡萄牙語義大利語瑞典語韓文Hsin-HsiChen5http://www.glreach.com/globstats/(StatisticsfromEuro-MarketingAssociates,1999)中文人口比例(6.1

4、%)<法文人口比例(8.8%)(1998年)Hsin-HsiChen6網路世界語言使用人口Hsin-HsiChen7網際網路內容(NetworkWizardsJan99InternetDomainSurvey)英語日語德語法語荷蘭語芬蘭語西班牙語中文瑞典語33,8781,6871,68465454647345843254640%的Internet使用者不懂英文，但是80%的Internet內容是英文Hsin-HsiChen8(Source:http://www.emarketer.com)Hsin-HsiChen9WhatisCross-LanguageInformationRetri

5、eval?Definition:Selectinformationinonelanguagebasedonqueriesinanother.TerminologiesCross-LanguageInformationRetrieval(ACMSIGIR96WorkshoponCross-LinguisticInformationRetrieval)TranslingualInformationRetrieval(DefenseAdvancedResearchProjectAgency-DARPA)Hsin-HsiChen10Generalization:Multi-&Cross-L

6、ingualInformationAccessHsin-HsiChen11MLIRApplicationsMultilingualinformationaccessinmultilingualcountry,organization,enterprise,etc.Cross-languageinformationretrievalforuserswhoreadasecondlanguage(largepassivevocabulary)butarenotabletoformulategoodqueries(smallactivevocabulary).Monolingualusersm

7、ayretrieveimagesbytakingadvantageofmultilingualcaptions.Monolingualusersmayretrievedocumentsandhavethemtranslated(automaticallyormanually)intheirlanguage.Hsin-HsiChen12WhyisCross-LanguageInformationRetrievalImportant?Moreinf