Large Scale Integration of Senses for the Semantic Web Jorge Gracia, Mathieu dAquin, Eduardo Mena Computer Science and Systems Engineering Department (DIIS)

Slides:



Advertisements
Similar presentations
COMP 110: Introduction to Programming Tyler Johnson Feb 11, 2009 MWF 11:00AM-12:15PM Sitterson 014.
Advertisements

COMP 110: Introduction to Programming Tyler Johnson Feb 18, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Feb 25, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Mar 16, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Apr 20, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Apr 13, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson January 12, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Mar 25, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Apr 8, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Apr 1, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Apr 27, 2009 MWF 11:00AM-12:15PM Sitterson 014.
COMP 110: Introduction to Programming Tyler Johnson Feb 4, 2009 MWF 11:00AM-12:15PM Sitterson 014.
Covert Barcodes handle on-the-spot Brand and Document Authentication Information Management Institute Conference on Security Printing 11/18/2009 Read what.
Solvency ii: an overview Lloyds May © LloydsSolvency II May Contents Solvency II: key features Legislative process Solvency II implementation.
2010 Tax Class1 Day 3 Class Participation Class Exercise – Paul Austin Publ W Exercise page 98 Advanced Section.
Tax Year TYPES OF PAYMENTS 1040 PG 2 Line & 68 Federal income tax withheld from W-2s, 1099s Estimated payments & $ applied from prior year.
ISDSI 2009 Francesco Guerra– Università di Modena e Reggio Emilia 1 DB unimo Searching for data and services F. Guerra 1, A. Maurino 2, M. Palmonari.
Remote Educational Programming Of Robots (REPOR) Tord Fauskanger Aurelie Aurilla Bechina Arntzen Dag Samuelsen Buskerud University College.
Federal Energy Regulatory Commission July Cyber Security and Reliability Standards Regis F. Binder Director, Division of Logistics & Security Federal.
…to Ontology Repositories Mathieu dAquin Knowledge Media Institute, The Open University From…
Perspectives on Academic Integrity Cases and Implications for Fostering Ethical Decision Making Ellen L. Landgraf, PhD., CPA, Associate Professor Loyola.
M. Mayer SEWG Fuel Retention June Sample Analysis for TS, AUG and JET: Depth Profiling of Deuterium M. Mayer Max-Planck-Institut für Plasmaphysik,
A Novel Visualization Model for Web Search Results An Application of the Solar System Metaphor Tien N. Nguyen and Jin Zhang Electrical and Computer Engineering.
Producing monthly estimates of labour market indicators exploiting the longitudinal dimension of the LFS microdata R. Gatto, S. Loriga, A. Spizzichino.
NOTEBOOKS ACCEPTABLE or NOT? March THINGS TO REMEMBER Must be Specific to the child. Consistent with the needs of the individual student. Personal.
The University of Manchester The University of Manchester CPHC Workshop, April The UK Schools Computer Animation Competition Toby Howard and Graham.
University of Reading Improved understanding of how rainfall responds to a warming world Richard Allan Environmental Systems.
Distributed Information System December 7, 20091Alvin MACCHIONE - Rémy JAVELLE.
9/09/20091 Risk Analysis Bob Sklar Engineering Fellow & Chief Engineer (Retired) Raytheon Company University of Arizona SIE-554 Fall 2009.
Wouter Noordkamp The assessment of new platforms on operational performance and manning concepts.
Privately Querying Location-based Services with SybilQuery Pravin Shankar, Vinod Ganapathy, and Liviu Iftode Department of Computer Science Rutgers University.
Quality Management for the Medical Laboratory
Student Learning Center Time Management Welcome to the Time Management workshop. While we are waiting to begin, please fill out the blank weekly.
Ziehm Academy - User Guide for online registration portal Nuremberg, February 2009.
October FUEL PRICE EVALUATION Comparing different fuel costs is a complex issue requiring an in-depth knowledge of fuel properties and characteristics,
Clarity Chromatography Software
Automation Solutions for Ladle Gate Applications
Working Set-Based Access Control for Network File Systems Stephen Smaldone, Vinod Ganapathy, and Liviu Iftode DiscoLab - Department of Computer Science.
Efficient Solutions For Water Supply Helix High-Pressure Vertical Multistage Pump.
Speed Limit Finder CS 410 Fall 2009 Personal Presentation September 21, 2009 Sept. 21,
1 Cathay Life Insurance Ltd. (Vietnam) 27/11/20091.
Combining Thread Level Speculation, Helper Threads, and Runahead Execution Polychronis Xekalakis, Nikolas Ioannou and Marcelo Cintra University of Edinburgh.
Presented by: Yaseen Ali, Suraj Bhardwaj, Rohan Shah Yaseen Ali, Suraj Bhardwaj, Rohan Shah Mechatronics Engineering Group 302 Instructor: Dr. K. Sartipi.
ATUG Roundtable – November 2009 NBN Architecture Reference Model.
IV Medicine Administration: Infection Control September 2009.
 Copyright 2006 Digital Enterprise Research Institute. All rights reserved. The Future is Now JeromeDL A Digital Library on Social Semantic.
1. (c) Alan Rowley Associates Laboratory Accreditation Dr Alan G Rowley Quality Policy based on Quality Objectives Quality Management System Communicate.
Vault 9 Project Update 9 th September 2009 Paul Pointon – Site Project Delivery Manager LLW Repository Ltd.
30 min Scratch July min intro to Scratch A Quick-and-Dirty approach Leaving lots of exploration for the future. (5 hour lesson plan available)
High Power Terminals & Connectors MAK8 & MAK12
Panel 3D = XML file pointer 08/09/20091 LHCb calorimeter meeting (jean-luc PANAZOL)
Mini_UPA, 2009 Rating Scales: What the Research Says Joe DumasTom Tullis UX ConsultantFidelity Investments
Flexible Scheduling of Software with Logical Execution Time Constraints* Stefan Resmerita and Patricia Derler University of Salzburg, Austria *UC Berkeley,
Agriculture: the Dog that Didn’t Bark? Tim Josling and Stefan Tangermann.
K eep I t C onfidential Prepared by: Security Architecture Collaboration Team.
Semantic Access to Data from the Web Raquel Trillo *, Laura Po +, Sergio Ilarri *, Sonia Bergamaschi + and E. Mena * 1st International Workshop on Interoperability.
Using Watson for Building Intelligent Applications in E-learning Mathieu d’Aquin The Knowledge Media Institute, The Open University
Exploiting the Semantic Web: Next Generation Semantic Web Applications in KMi Watson, PowerMagpie, PowerAqua, … Mathieu d’Aquin Laurian Gridinoc Vanessa.
Temporal Event Map Construction For Event Search Qing Li Department of Computer Science City University of Hong Kong.
An Integrated Approach to Extracting Ontological Structures from Folksonomies Huairen Lin, Joseph Davis, Ying Zhou ESWC 2009 Hyewon Lim October 9 th, 2009.
Automatic Lexical Annotation Applied to the SCARLET Ontology Matcher Laura Po and Sonia Bergamaschi DII, University of Modena and Reggio Emilia, Italy.
Towards an ecosystem of data and ontologies Mathieu d’Aquin and Enrico Motta Knowledge Media Institute The Open University.
Q2Semantic: A Lightweight Keyword Interface to Semantic Search Haofen Wang 1, Kang Zhang 1, Qiaoling Liu 1, Thanh Tran 2, and Yong Yu 1 1 Apex Lab, Shanghai.
A Systemic Approach for Effective Semantic Access to Cultural Content Ilianna Kollia, Vassilis Tzouvaras, Nasos Drosopoulos and George Stamou Presenter:
Web Information Retrieval Prof. Alessandro Agostini 1 Context in Web Search Steve Lawrence Speaker: Antonella Delmestri IEEE Data Engineering Bulletin.
And the Watson Plugin for the NeOn Toolkit. IST NeOn-project.org The Semantic Web is growing… #SW Pages.
Your caption here POLYPHONET: An Advanced Social Network Extraction System from the Web Yutaka Matsuo Junichiro Mori Masahiro Hamasaki National Institute.
Cross-Ontological Relationships
Actively Learning Ontology Matching via User Interaction
Presentation transcript:

Large Scale Integration of Senses for the Semantic Web Jorge Gracia, Mathieu dAquin, Eduardo Mena Computer Science and Systems Engineering Department (DIIS) University of Zaragoza, Spain Knowledge Media Institute (KMi) Open University, United Kingdom Jorge Gracia, Mathieu dAquin, Eduardo Mena Computer Science and Systems Engineering Department (DIIS) University of Zaragoza, Spain Knowledge Media Institute (KMi) Open University, United Kingdom 18th International World Wide Web Conference Madrid, Spain, 20th-24th April 2009

WWW Outline Introduction Method Optimization study Experiments Conclusions

WWW Introduction Current Semantic Web Favoured by the increasing amount of online ontologies already available on the Web Hampered by the high heterogeneity that this growing semantic content introduces The redundancy problem Excess of different semantic descriptions, coming from different sources, to describe the same intended meaning Our proposal A method to cluster the ontology terms that one can find on the Semantic Web, according to the meaning that they intend to represent

WWW Introduction

WWW Introduction

WWW Redundancy problem: many representations of the same meanings ? Watson apple Introduction The Semantic Web

WWW Proposed solution: pool of cross-ontology integrated senses clustered Watson apple Introduction The Semantic Web The Fruit The Tree The Company

WWW Introduction Watson The Semantic Web Multiontology Semantic Disambiguator Ontology Evolution Semantic Browsing Scarlet Ontology Matching Folksonomy Enrichment QueryGen Semantic Query Generation Question Answering

WWW Ontology terms Synonym expansion integration Sense clustering Keyword maps Synonym maps Senses (each synonym map) Watson Similarity > threshold? more ont. terms? yes no Extraction Similarity Computation rise threshold? Integration Senses Clustering Disintegration yesno Modify integration degree CIDER Modify integration? yes Method OFF-LINE RUN-TIME

WWW Keyword maps: ontology terms with identical label Watson Method apple

WWW Synonym maps: ontology terms with synonym labels apple apple tree Apple Inc. apple tree manzana Watson Method

WWW Method Agglomerative clustering CIDER a b c d a d a b c a d a b c... e e e

WWW Sense maps: semantically equivalent terms grouped apple Apple Inc. apple tree manzana apple Apple Inc. apple The Fruit The Tree The Company apple tree apple CIDER Method

WWW Falling threshold (Integration) Rising threshold (Disintegration) Optimal threshol d Method

WWW Integration level varies with similarity threshold Optimization study Integration Level = 1 - # finalSenses / # initialOntologyTerms

WWW Which similarity threshold is the best one? Three exploration ways: Experimenting with ontology matching benchmarks Obtained 0.13 lower bound for optimal threshold Contrasting with human opinion Range of good values between 0.2 and 0.3 Optimizing time response. Because: It will reduce the response time of the overall system Compatible with the other two ways It is not always feasible to have a large enough number of humans to ask or reference alignments Optimization study

WWW Response time varies with threshold Optimal value around 0.22 Optimization study

WWW Scalability study 9156 keywords, different ontology terms to be clustered, Processing time is linear with number of ontology terms Experiments

WWW Scalability study Processing time is independent of ontology size Experiments

WWW Illustrative example Keyword = turkey Synonym map = turkey, Türkei, Türkiye Nº ontology terms = 58 Nº Integrated senses = 9 (threshold = 0.27) Experiments

WWW Experiments More examples (threshold = 0.19) Keyword#initial terms#final senses appalachian71 apple397 free512 mace73 plant5218 poll54 stein51 turkey588

WWW Experiments Positive facts Terms from different versions of the same ontology are easily detected Very different meanings are not wrongly integrated (e.g., plant as living organism with plant as industrial buildings) Negative facts Hard to obtain a total integration of the same meanings (caused by very different semantic descriptions)

WWW Conclusions Redundancy of semantic descriptions on the Web can be significantly reduced Our integration technique scales when used on a large body of knowledge The proposed method is flexible enough to configure and adapt our integration level to the necessities of client applications Future work More advanced prototype More extensive human-based evaluation Study and evaluation of impact on other systems Conclusions

WWW END of presentation Thank you!