Transcription
UNIVERSALNETWORKINGLANGUAGEUNDL FOUNDATION
UNLBAMAKO7/05/05
Content1.2.3.4.5.6.7.Seeing is believingResponse to challenge of our timeConvergence of IT, Knowledge, LanguageWhat we can do with itHow it worksWhat it takes to have itA story
CHRUSSIANRUSSIANSPANNISHSPANNISH
UNITED NATIONS: 5x6 30 PairsFrenchChineseRussianSpanishEnglishArabic
chRussianJapaneseEtc.Arabic
EnconverterFrenchEtc.Arabic
UNL System ArchitectureFrenchUNLSystemChineseChinese PeopleFrench PeopleArabicHindiInternetHindu PeopleThe property rights of the UNL belongs to the United NationsArabic People UNDL Foundation. All rights reserved
UNL Document creationWEBInternetWeb serverWeb pageusing UNLSpanish ContentDeveloperEnconvertingUNL LanguageServerSpanish
Language ServerWeb Server withUNL uralLanguageLanguage ServerDECOKnowledgeBase
UNL-LanguageDictionaryKnowledgeBaseGenerationRules
uageDictionaryKnowledgeBase
UNL LANGUAGE SERVEREnconverter Í Î Deconverter(EnCO)(EnCO)Language ServerUNL - ChineseEnCODeCOUNL documentLanguage ServerUNL EditorUNL - ArabicUNL ViewerUNL ProxyLanguage ServerInternetUSER1UNL - Spanish23Language ServerUNL - HindiLanguage ServerUNL - JapaneseEnCODeCOLanguage ServerUNL - EnglishEnCODeCOEnCODeCO
LANGUAGE SERVERUNL Í Î Native LanguageEnconversion Program3EnCOUNL DictionaryDeconversion ProgramDeCOUNL GrammarUNL Knowledge Base
The UNL over the WebWEBUNLFrenchFrenchUNLUNLHindiFrench PeoplesinehCe Chinese PeopleUNLUNLSpanishRussianEnglishHindiHindu PeopleChinese UNL Language serverSpanishSpanish People
MERCIThank you
History of Great Discoveries and theGreat Inventions To see the Forest beyond the Trees. The little stories of everyday, hide the great history andthe great changes in History Most of them are unexpected Technology are response , reaction to great challenges– Technologies has a power of transforming everything,catalyzes of other movements, power of multiplying effects,opportunities;– Technologies that have higher lower power of transforminglife;– When they happen , there is a Risorgimento regional.
UNLFrenchJapaneseEtc.Arabic
What the UNL can do ?1) Machine Translation2) Multilingual Information Service (eCommerce, e-learning, e-government,e-TV)3) Information Retrieval System (eCommerce, e-learning, e-government)4) Expert system5) Encyclopaedia6) And many others
Inside the UNL SystemWHAT IS THE UNL ?A set of resourcescomprising:– Linguistic Resources– A technical infrastructure– Knowledge Assets
Linguistic resources Specifications of the UNL– Universal Words (UWs)– Master Definitions– Attributes– Relations– Grammar
Technical Resources UNL Servers– Enconverter– Deconverter Proxy Server UNL Editor UNL Verifier UNL Explorer Manuals
Knowledge Assets Dictionaries: UWs, Master, NaturalLanguage (NL) Grammatical rules for each NL
Competitors? Computer systems which can dealwith knowledge and contents havebeen already developed. Representations of knowledge orcontents are different from eachother. Moreover, a representation dependson a language. Knowledge or contents of acomputer system can not be used in
Who? In the case of machine translation,if we combine all the results ofresearch and development onmachine translation, we can notrealize a multilingual machinetranslation system that can breaklanguage barriers.
Advantages of UNL The UNL, a common language forcomputers:– enables sharing knowledge andcontents among all systems– overcomes language barriers– reduces costs of developing knowledgeor contents– facilitates knowledge processing
How it works The UNL can express concepts likewords do in natural languages. Ex:horse, cavalo, cheval,(Chineseideogram), The UNL can express informationlike natural languages do. Ex: fulldescription of a horse as in anencyclopaedia entry.
How UNL express information? The UNL express information byclassifying objectivity andsubjectivity. Objectivity is expressed using UWsand relations. Subjectivity is expressed usingattributes.
Who are wez300 computer scientists and linguists fromuniversities and research institutions aroundthe world
Language Coverage Languages already engaged: 6 UN official Languages:Arabic, Chinese, English, French,Spanish, Russian Other languages:Hindi, Indonesian, Italian,Japanese, Korean, Mongol,Latvian, Portuguese, Thai
UNL R&D Network(1)ArabicThe Royal Scientific Society, JordanChineseMinistry of Electronics Industry, ChinaEnglishUNL CentreFrenchUniversity Joseph Fourier, FranceGermanUniv. of Saarbrucken, Germany (inactive)HindiIndian Institute of Technology, IndiaIndonesian BPPT Technology, IndonesiaItalianPisa CNR, ItalyJapaneseUNL Centre
UNL R&D Network(2)MongolianMongol Pedagogical University, MongoliaLatvianUniversity of Latvia, Latvia (inactive)Portuguese University of Sao Paulo, BrazilRussianRussian Academy of Science, RussiaSpanishUniversity Politecnica of Madrid, SpainSwahiliUniv. of Dar es Salaam, Tanzania (inactive)ThaiNECTEC, Thailand (inactive)UNL Centre UNDL Foundation
Where we are now1) UNL the language, Relation and Attributes(specification)Version Approved by a committee ofScholars and patent recognized by PCTcountries (WIPO) 2002Dictionary of Universal Words, KnowledgeBase (Increasing volume of entries on acontinuous development)
Where we are now2) Language Server: (Operational)a) Deconverter (Language Generation System)Deco: OperationalGeneration Rules and Dictionary (eachlanguage):continuous developmentb) Enconverter (UNL Generation System)Enco: OperationalAnalysis Rules, Dictionaries (each language):continuous development
Where we are now 3) Tools & Applications: UNL Proxy Server: OperationalUNL News: 4 publications on 2002UW Gate: under testsUNL Verifier: under testsUNL Viewer: PrototypeUNL Editor: PrototypeUNL Encyclopedia: PrototypeUNL Explorer: PrototypeOrg Explorer: Prototype
Vision of the Future Applications in all fields of humanactivities Advantages for internationalorganizations Bridging the Digital Gap Benefits for Multilingual Countries Content driven Technology: hence opportunities for employment andself employment Low cost clean investment
Challenges Financial Resources Persistence: working towardscumulative results More language coverage Expanding the R&D network
Open PolicyUNL (system) should be developed byall peoples in the world. We will open:UNL specificationsUniversal Word DictionaryFormat of UNL-Language dictionaryFormat of Deconversion ruleSystem interface
What we expect to be developed bypeople in the worldUNL (system) should be developed byall peoples in the world. Universal words necessary for eachlanguage Language Servers for new languagesand new domains
What we expect to be developed bypeople in the world Application systems such as:Information Retrieval SystemSearch EnginesBrowsersEditors/Word ProcessorsMachine translation Systems
The UNL System1) UNL (Universal Networking Language)Dictionary of Universal Words , Relation, Attribute,Knowledge Base2) Language Serveri) Deconverter (Language Generation System)Deco, Generation Rules, Dictionary(eachlanguage)ii) Enconverter (UNL Generation System)Enco, Analysis Rules, Dictionaries(eachlanguage)3) Tools: UNL Viewer UNL Editor UNL Proxy Server
UNL Proxy Server Searches for UNL at the web pageaccessed by the user. The UNL document is sent to theLanguage Server defined by theselected language. Updates the web page to be displayedon the user’s chosen language.
UNL Editor
paneseEtc.ArabicDeconverter
UNL Editor – select sentence
UNL Editor
UNL Editor
UNL Editor
UNL Editor
UNL Encyclopaedia
UNL Encyclopaedia “Infinite library” (M.Luis Borges)Human KnowledgeKnowledge systemEncyclopaediasHow to build the UNL Encyclopaedia
UNL Patent Purpose: Gift to Humankind Submitted in 1999 to the JapanesePatent Office Recognized by PCT countries(WIPO) 2002 Application for patent ecommercial protection in majorcountries Protection by the United Nations
UNL Global Network of R&D 300 computer scientists andlinguists from universities andresearch institutions around theworldLanguages covered: Arabic,Chinese, English, French,Japanese, German, Hindi,Indonesian, Italian, Latvian,Mongolian, Portuguese, Russian,Si h Th i
UNL Society Purpose: Collaboration in R&D Membership: Individual andinstitutions At present: over 300 membersfrom 30 countries Future perspective: Collaboration,support users
WE A global network ofcomputer Scientistsand Linguists philosophers,mathematicians UNDL FOUNDATION8, JULY 2003
UNL: A LANGUAGE UNL is a “language” for computers (differentfrom a “computer language”) expresses information and knowledge indigits, the characters that all computersunderstands enconverts contents from any naturallanguage into UNL and then deconverts intoany other natural languages. UNL Language enables peoples to build the “reservoir” of human knowledgefrom and to diverse natural languages
paneseEtc.ArabicDeconverter
chRussianJapaneseEtc.Arabic
chRussianJapaneseEtc.Arabic
UNL: A SYSTEM UNL has been designed torepresent contents in alanguage independent way. UNL is a system to supportmultilingual informationservices (mainly for Internet) It can also be used as amachine translation system
European Heritage Network(HEREIN) HEREIN is a very large document repository (all documentswritten in three different languages)Great amount of human translation resources needed.Current contents written in UNL can be converted in morelanguages. Web page www.european-heritage.net The Network is currently composed of administrations and/ormandated bodies from the following (27) countries :– Andorra, Armenia, Belgium (Brussels-Capital, Flemish Region,Walloon Region), Bulgaria, Croatia, Cyprus, Denmark, Estonia,Finland, France, Georgia, Hungary, Ireland, Latvia, Lithuania,Luxembourg, Norway, Poland, Portugal, Romania, Slovakia,Slovenia, Spain, Sweden and the United Kingdom.
DEMO1. See the Spanish report (.xml)2. See the Spanish report in UNL3. Load the Spanish report in UNL into theSpanish language generator.4. See the generated Spanish (output.txt)5. See generation available in otherlanguages (Russian, English, Italian).
THE SIZE OF THE PROBLEM/CHALLENGEGlobalization of the economic activities and the political relationsamong states and social lifestyle is generated, supported andreinforced by global information systems.The global village emerging from the convergence oftelecommunications carriers, radio and television global networksand the computers generates the conditions for a market, sharingaffluence, and enjoying cultural goods.The global village creates the situation of exclusion of millions fromthe sharing affluence, health services education, enjoying leisure,technology comfort exchange and exposure culture, participatingsocial activities, benefiting from economic activities, access to themarket
Population Forecasts for Major Cities in 2010 (unit: millions)(1) Tokyo (Japan)(2) San Paolo (Brazil)(3) Bombay (India)(4) Shanghai (China)(5) Lagos (Nigeria)(6) Mexico City (Mexico)(7) Beijing (China)(8) Dhaka (Bangladesh)(9) New York (USA)(10) Jakarta (Indonesia)(11) Karachi (Pakistan)(12) Manila (Philippines)(13) Ten shin (China)28.93 m24.97 m24.37 m21.67 m21.09 m18.02 m17.97 m17.55 m17.23 m17.20 m17.02 m16.06 m15.70 m(14) Calcutta (India)(15) New Delhi (India)(16) Los Angeles (USA)(17) Seoul (South Korea)(18) Buenos Aries (Argentina)(19) Cairo (Egypt)(20) Rio de Janeiro(Brazil)(21) Bangkok (Thailand)(22) Tehran (Iran)(23) Istanbul (Turkey)(24) Osaka (Japan)(25) Moscow (Russia)(26) Lima (Peru)15.70 m15.58 m13.91 m13.91 m13.68 m13.42 m13.32 m12.74 m11.88 m11.80 m10.60 m10.37 m10.07 m252319227 17131115 824 143 14 211210916652622018Source: World Bank Data/Nishi
Top 10 Languages byPopulationRANKLANGUAGE POPULATION1. CHINESE (MANDARIN)885,000,0002. SPANISH332,000,0003. ENGLISH322,000,0004. BENGALI189,000,0005. HINDI182,000,0006. ARABIC (ALL COUNTRIES)177,000,0007. PORTUGUESE170,000,0008. RUSSIAN170,000,0009. JAPANESE125,000,00010. GERMAN, STANDARD98,000,000Source: Ethnologue: Languages of the World
WHAT DOES UNL OFFER?The UNL provides users with a multilingual platform and aset software tools enabling them to communicate withother people their respective languages.With the multilingual platform in place, users can shareinformation and knowledge across native languages.Citizens, governments, international organizations, andenterprises will all benefit from the UNL, as it providesopportunities for information sharing, education, and ebusiness. The ultimate goal is to promote sustainabledevelopment, dialogue among civilizations, economicprosperity for all nations as well as peace among them.The property rights of the UNL belongs to the United Nations UNDL Foundation. All rights reserved
UNL LANGUAGE SERVERUNL LANGUAGESERVEREnconverterÍ Î DeconverterEnconverterÍ Î (EnCO)Deconverter(EnCO)(EnCO)(EnCO)Language ServerLanguageServerUNL - ChineseUNL - ChineseEnCOEnCOUNL documentUNL documentUNL EditorUNL EditorLanguage ServerLanguage ServerUNL - ArabicUNL - ArabicUNL ViewerUNL ViewerUNL ProxyUNL ProxyInternetInternet11USERUSERDeCO
UNL Proxy Server Searches for UNL at the web page accessed by the user. The UNL document is sent to the Language Server defined by the selected language. Updates the web page to be displayed on the user’s chosen language.