Presentation is loading. Please wait.

Presentation is loading. Please wait.

SEmantic Knowledge Technology

Similar presentations


Presentation on theme: "SEmantic Knowledge Technology"— Presentation transcript:

1 SEmantic Knowledge Technology http://sekt.semanticweb.org
SEKT SEmantic Knowledge Technology

2 SEKT addressing the semantic knowledge technology research agenda
6th framework IP project start date 1/1/2004 36 months, €12.5m sekt.semanticweb.org

3 Key people Project Director – John Davies, BT
Technical Director – Rudi Studer, Karlsruhe Project Manager – Paul Warren, BT Project Management Board Marko Grobelnik, JSI Ralph Traphoener, Empolis Hamish Cunningham, Sheffield Juergen Angele, Ontoprise Atanas Kiryakov, SIRMA AI Jesus Contreras, iSOCO Tom Boesser, kea-pro Pompeu, UAB Frank van Harmelen, VUA Jos De Bruijn, DERI Innsbruck

4 The Goal To deliver next generation semantic knowledge technology through: Foundational research (Semi-)automatic ontology generation and population Ontology management (mediation, evolution, inferencing) Innovative technology development A suite of knowledge access tools Open source ontology middleware platform Validated by 3 case studies and benchmarking/usability activties Supported by a methodology

5 XML is a first step Semantic markup Metadata
HTML  layout prescription XML  content prescription Metadata within documents not across documents prescriptive

6 RDF, RDFS & OWL Standards of W3C Descriptive
RDF consisting of triples or sentences: <subject, property, object> <prod341, price, €54000>, <org176, sells, prod341> RDF & RDFS used to define and populate ontologies OWL – based on DL, more expressive, inference capabilities, 3 dialects

7 A (simple) example “Tolkien wrote ‘The Hobbit’ ”
hasWritten (‘ “A famous writer is a kind of writer” subclassof(FamousWriter, Writer) “ ‘The Hobbit’ is a book” type(‘

8 Semantic Web & KM Making WWW information machine processable
annotation via ontologies & metadata offers prospect of enhanced knowledge management “Rank all the documents containing the word Tolkien” “Show me the non-fiction books written by Tolkien about philology before 1940” significant research & technology challenges are outstanding

9 Annotation is a potential bottleneck
… and how do we handle legacy knowledge? We need automation: semi-automatic learning of ontologies (KD) semi-automatic generation of metadata (HLT) maintaining and evolving ontologies (OMT) a multi-disciplinary approach

10 Major RTD challenges Improve automation of ontology and metadata generation Research and develop techniques for ontology management and evolution Develop highly-scalable solutions Research sound inferencing despite inconsistent models Develop semantic knowledge access tools Develop methodology for deployment

11 Key outcomes technological progress through development of leading edge, integrated semantically-enabled KM software tools scientific progress through foundational research creation of awareness via dissemination, training, case studies

12 Key outcomes building the European Research Area in KM through collaboration with related IP and NoE projects in this area for a coordinated impact strategy SEKT, DIP, KnowledgeWeb – SDK cluster sdk.semanticweb.org Collaboration with other projects – PASCAL, ALVIS, ECOLEAD, …

13 Multidisciplinary approach
KD/HLT Management & evolution KD/HLT Need to determine appropriate technology mix Semi-automatic

14 Human Language Technology
Aim: bring together the current text-based web and the formal knowledge underlying Semantic Knowledge Technologies increase the adaptivity of the metadata generation tools to evolving end-user information needs Language processing tools automating to a large degree the production of metadata dealing with the large scale of the Web supporting multiple languages supporting learning from unlabeled data, using KD

15 Knowledge Access context-aware tools for access to semantically-annotated knowledge search, browse, visualise, summarise, share, infer integrated into day-to-day business processes automatic knowledge delivery based on current context (activity, location, device, interests) support multiple end-user devices also support for on-the-fly metadata creation metadata creation as a side-effect of data creation

16 Feedback/forward – 3 case studies
helping newly-appointed judges helping IT consultants a corporate digital library Use/refinement of SEKT methodology Usability, business benefits and benchmarking

17 Resulting software should
Integrate with day-to-day business processes automatic knowledge delivery based on current context and activity Support on-the-fly metadata creation metadata creation as a side-effect of data creation Have a natural and intuitive user interface

18 Dissemination & Exploitation
SDK project cluster sdk.semanticweb.org SEKT, DIP, KnowledgeWeb 1st European Semantic Web Symposium delivered Multiple publications, press articles Project poster, presentation, brochure Exploitation Systems integrator Several software vendors Sector-specific organisations Open source v. software products

19 Project Overview

20 The inSEKTs Empolis University of Sheffield Universität Karlsruhe BT
Vrije Universiteit Amsterdam Empolis University of Sheffield Universität Karlsruhe BT Ontoprise Kea-pro Universität Innsbruck iSOCO Sirma AI Universitat Autònoma de Barcelona Jozef Stefan Institute

21 Thank you for your time Any questions? john.nj.davies@bt.com
PAAM 96 Tutorial Thank you for your time Any questions? Copyright British Telecommunications plc 1996 31

22

23 Limitations of the Web today
Machine-to-human, not machine-to-machine


Download ppt "SEmantic Knowledge Technology"

Similar presentations


Ads by Google