WP1: Plan for the remainder (1) Ontology –Finalise ontology and lexicons for the 2 nd domain (RTV) Changes agreed in Heraklion –Improvement to existing.

Slides:



Advertisements
Similar presentations
Controlled Vocabularies in TELPlus Antoine ISAAC Vrije Universiteit Amsterdam EDLProject Workshop November 2007.
Advertisements

Coursework.  5 groups of 4-5 students  2 project options  Full project specifications on 3 rd March  Final deadline 10 th May 2011  Code storage.
© NCSR, Paris, December 5-6, 2002 WP1: Plan for the remainder (1) Ontology Ontology  Enrich the lexicons for the 1 st domain based on partners remarks.
Enabling Access to Sound Archives through Integration, Enrichment and Retrieval WP1. Project Management.
Francesca Fallucchi, Noemi Scarpato,Armando Stellato, and Fabio Massimo Zanzotto DISP, University “Tor Vergata” Rome, Italy
Using the Semantic Web to Construct an Ontology- Based Repository for Software Patterns Scott Henninger Computer Science and Engineering University of.
Xyleme A Dynamic Warehouse for XML Data of the Web.
Mastering the Internet, XHTML, and JavaScript Chapter 7 Searching the Internet.
/ department of mathematics and computer science TU/e eindhoven university of technology CEDEFOP workshop: Policy, Practice, Partnership: Getting to Work.
Direct Congress Dan Skorupski Dan Vingo 15 October 2008.
FACT: A Learning Based Web Query Processing System Hongjun Lu, Yanlei Diao Hong Kong U. of Science & Technology Songting Chen, Zengping Tian Fudan University.
Presentation for IST June. 02 Brian Foley, TecNet, Ireland Page 1 Introduction TEAMwork TEAMwork Project (IST )
A global multidisciplinary network on housing research and learning WP3 Report Leandro Madrazo La Salle School of Architecture Barcelona, Spain Tirana,
Aurora: A Conceptual Model for Web-content Adaptation to Support the Universal Accessibility of Web-based Services Anita W. Huang, Neel Sundaresan Presented.
FP OntoGrid: Paving the way for Knowledgeable Grid Services and Systems WP8: Use case 1: Quality Analysis for Satellite Missions.
Break Out Session on Infrastructure and Technology: A Report Vipul Kashyap AOS Workshop, Rome, 15 November 2001
13 ° COSMO General Meeting Rome VERSUS2 Priority Project Report and Plan Adriano Raspanti.
Institute of Informatics and Telecommunications – NCSR “Demokritos” Bootstrapping ontology evolution with multimedia information extraction C.D. Spyropoulos,
8th meeting of the Task Force on Health Expectancies Session 1 – Update from the Commission SILC/EHIS update/EDSIM.
WP6 – Information Extraction Introduction to MedIEQ Quality Labelling of Medical Web content using Multilingual Information Extraction
FLAVIUS Technical presentation (Overblog, Qype, TVTrip) - WP2 Platform architecture.
Final Review 31 October WP2: Named Entity Recognition and Classification Claire Grover University of Edinburgh.
11111 Benchmarking in KW. Sep 10th, 2004 © R. García-Castro, A. Gómez-Pérez Raúl García-Castro, Asunción Gómez-Pérez September 10th, 2004 Benchmarking.
CROSSMARC Web Pages Collection: Crawling and Spidering Components Vangelis Karkaletsis Institute of Informatics & Telecommunications NCSR “Demokritos”
EuroRoadS for JRC Workshop Lars Wikström, Triona Editor of EuroRoadS deliverables D6.3, D6.6, D6.7.
 Copyright 2005 Digital Enterprise Research Institute. All rights reserved. Semantic Web services Interoperability for Geospatial decision.
Dissemination of results Updating WP 2 Quality Labeling of Medical Web Content Using Multilingual Information Extraction (MedIEQ) Barcelona meeting 1-2.
CORPORUM-OntoExtract Ontology Extraction Tool Author: Robert Engels Company: CognIT a.s.
HYGIA: Design and Application of New Techniques of Artificial Intelligence for the Acquisition and Use of Represented Medical Knowledge as Care Pathways.
University of Sheffield NLP Teamware: A Collaborative, Web-based Annotation Environment Kalina Bontcheva, Milan Agatonovic University of Sheffield.
Semantic Technologies & GATE NSWI Jan Dědek.
Edinburg March 2001CROSSMARC Kick-off meetingICDC ICDC background and know-how and expectations from CROSSMARC CROSSMARC Project IST Kick-off.
European Commission DG Enterprise VIRTUAL ENVIRONMENT FOR INNOVATION MANAGEMENT TECHNIQUES VERITE Kick-off meeting Thessaloniki November 2001.
Work package 7 Dissemination and Concertation EuropeanaConnect Plenary Meeting Berlin, May 2010 Monika Segbert, Eremo srl.
LEONARDO TRANSFER OF INNOVATION PROJECT “MEDIA TECH: The future of media industry using innovative technologies ” No. LLP-LdV-ToI-11-CY Kick-off.
6-7 / 3 /2006 INSEAD Campus - Fontainebleau WP5: Exploitation and Dissemination General approach and scheduling on deliverable: D5.1 Dissemination and.
Project Overview Vangelis Karkaletsis NCSR “Demokritos” Frascati, July 17, 2002 (IST )
Maintaining Information Integration Ontologies Georgios Paliouras, Alexandros Valarakos, Georgios Paliouras, Vangelis Karkaletsis, Georgios Sigletos, Georgios.
Trustworthy Semantic Webs Dr. Bhavani Thuraisingham The University of Texas at Dallas Lecture #4 Vision for Semantic Web.
Towards a Glossary of Activities in the Ontology Engineering Field Mari Carmen Suárez-Figueroa and Asunción Gómez-Pérez {mcsuarez, Ontology.
>lingway█ Solutions in language processing Lingway & Crossmarc exploitation plan José Coch.
© NCSR, Frascati, July 18-19, 2002 WP1: Plan for the remainder (1) Ontology Ontology  Use of PROTÉGÉ to generate ontology and lexicons for the 1 st domain.
September 25, 2006 NASA Feasibility Study Status Update.
NCSR “Demokritos” Institute of Informatics & Telecommunications CROSSMARC CROSS-lingual Multi Agent Retail Comparison Costas Spyropoulos & Vangelis Karkaletsis.
Responsibilities and tasks EcoR Partener P6 - EcoR Partener CRPMPEC Canakkale, Turkiye 15th, 2011,September 16’th - IMPLEMENTATION OF A QUALITY ASSURANCE.
Semantic web Bootstrapping & Annotation Hassan Sayyadi Semantic web research laboratory Computer department Sharif university of.
Michel Van Hoegaerden Programme Manager EU Expert Group 16/11/10, Brussels Joint Action on Health Workforce Planning and Forecasting STATUS BRIEFING.
>lingway█ >Lingway Fact Extractor (LFE)█ >Introduction >Goals Crossmarc / Lingway >Lingway adaptation of the NHLRT approach >Rule induction >(ongoing work)
Worldwide Protein Data Bank Common D&A Project Sequence Processing Modular Demo May 6, 2010 Project Deliverable.
The Education Framework (or: What’s going on in the education area) Jörg Diederich (L3S) Berlin meeting, 2007.
EUROSTAT REPORT ON DISSEMINATION ACTIVITIES 1st Quarter 2004 Dissemination Working Group April 2004 Christine Kormann.
WP1: Application Ontology Management Maria Teresa Pazienza Dept. Of Computer Science University of Rome “Tor Vergata”
Institute of Informatics & Telecommunications NCSR “Demokritos” Spidering Tool, Corpus collection Vangelis Karkaletsis, Kostas Stamatakis, Dimitra Farmakiotou.
© NCSR, Frascati, July 18-19, 2002 CROSSMARC big picture Domain-specific Web sites Domain-specific Spidering Domain Ontology XHTML pages WEB Focused Crawling.
WP1.4 Index and Search George Kakaletris University of Athens.
NCSR “Demokritos” Institute of Informatics & Telecommunications CROSSMARC CROSS-lingual Multi Agent Retail Comparison WP3 Multilingual and Multimedia Fact.
5 th -6 th December th Meeting Paris WP2: NERC.
Brussels, January 16th, Overview and status of the project.
WP8: Demonstrators (UniCam – Regione Marche)
WP15- Dissemination & Exploitation INMARK
Working meeting of WP4 Task WP4.1
 Corpus Formation [CFT]  Web Pages Annotation [Web Annotator]  Web sites detection [NEACrawler]  Web pages collection [NEAC]  IE Remote.
Usage scenarios, User Interface & tools
Institute of Informatics & Telecommunications NCSR “Demokritos”
Institute of Informatics & Telecommunications
ESSnet on SDMX phase II Laura Vignola
The basics ESSnet on SDMX prepared in 2008/2009
Month 43: June 2016 – Month 50: January 2017 Remaining Deliverables
Review plan of the nature reporting – update 6
Reportnet 3.0 Database Feasibility Study – Approach
Presentation transcript:

WP1: Plan for the remainder (1) Ontology –Finalise ontology and lexicons for the 2 nd domain (RTV) Changes agreed in Heraklion –Improvement to existing functionalities, development of new ones in Protégé (RTV) Nodes ids, import/export, FE schema generation, stereotyped editor, … –Customisation tools and methodology (using the same ontology + lexicons schema, create through Protégé the new ontology and lexicons and the new FE schema) (RTV) Specify measurements for customisation Examine in new domains applying the measurements –Relevant section in D1.3(b) (2 nd domain, improvements, customisation tools and methodology, …) (RTV) Draft Final

WP1: Plan for the remainder (2) Corpus formation for the needs of page filtering –Customisation methodology Specify measurements Examine in new domains, apply measurements –Relevant section in D1.3(b) (2 nd domain, customisation methodology) (NCSR) Draft Final

WP1: Plan for the remainder (3) Web spidering (NEAC) –Incorporate WebXimmler Examine whether there are relevant commercial products Examine WebXimmler in both domains New version of WebXimmler to handle the remaining 20% (javascripts, …), problems with charsets XML vs XHTML output (is WebXimmler output appropriate for all partners ?) –Incorporate Language Identification Module (LIM) EDIN’s LIM improvement, evaluate in both domains Examine other LIMs Speed performance tests Updates in NEAC (apply LIM in each visited page, add a meta-tag when saving the page)

WP1: Plan for the remainder (4) Web spidering (NEAC) –Finalise site navigator Handle the rest of the navigation cases (javascript, search forms) Examine in both domains –Page filtering Evaluation for the 2 nd domain in all 4 languages Customisation methodology (specify measurements, examine in new domains) –Link scoring Evaluation for the 2 nd domain in all 4 languages Customisation methodology (specify measurements, examine in new domains) –Relevant section in D1.3(b) (NCSR) Draft Final

WP1: Plan for the remainder (5) Focused Crawling Tool –Evaluation of the integrated tool (EDIN crawler + NEAC-light) in the 4 languages both domains –Customisation methodology Specify measurements, Examine in new domains, apply measurements –Relevant section in D1.3(b) (new version, evaluation in both domains, customisation methodology) Draft Final

WP1: Plan for the remainder (6) Other tools for web pages collection –Cross-merge NCSR, RTV version, documentation Integrated web pages collection system –Report modifications(due to agents strategy and support of more than one domain) –Relevant section in D1.3(b)

WP1: Plan for the remainder (6) Corpus collection for the needs of NERC and FE –Report on the corpus collection task for 2 nd domain for D1.3(b) Web Annotator –Customisation methodology –Relevant section in D1.3(b) (final version, customisation methodology)

WP1: Plan for the remainder (8) User Evaluation –Experiment with new Web UI for focused crawling, spidering – Possible improvements Deliverable D1.3(b) –Template –Draft –Final

WP2: Plan for the remainder (1) NERC DTD –Specifying NERC DTDs for new domains Guidelines, Examine in new domains Relevant section in D2.4 Corpus annotation for the needs of NERC –Final NERC annotation guidelines for the 2 nd domain based on the partners remarks during the annotation task –Relevant section in D2.4

WP2: Plan for the remainder (2) NERC v.3 (incorporation of mechanisms for rapid adaptation to new domains) –Exploit machine learning techniques for each language EDIN (max entropy, …), Lingway (induction of rules to support knowledge engineer, …), NCSR (Decision trees, TBEDL-Brill, Combination), RTV (lexicon acquisition to enrich lexicons/gazetteers, …) Application and evaluation in both domains for each partner –Customisation methodology Template for relevant section in D2.4 Specify measurements Application in new domains Report per partner Integrated report on a NERC customisation methodology –Relevant section in D2.4

WP2: Plan for the remainder (3) NERC-based demarcator (NCSR) –Compare the rule-based version with the ML-based one in both domains –Customisation methodology Specify measurements Examine in new domains –Delivery of Demarcator application to the partners –Relevant section in D2.4

WP2: Plan for the remainder (4) Deliverable 2.4 –Template –Draft –Final

WP3: Plan for the remainder (1) FE schema –Final corrections to FE schema for 2 nd domain –Specifying FE schemas for new domains through Protégé Guidelines, Examine in new domains Relevant section in D3.2 Corpus annotation for the needs of FE –Final Fact annotation guidelines for the 2 nd domain based on the partners remarks during the annotation task –Relevant section in D3.2

WP3: Plan for the remainder (2) FE v.2 –WHISK (RTV) Provide the WHISK v.1 application to the partners (specify the necessary modules) Relevant section in D3.2 Normalisation –Evaluation results per partner –Relevant section in D3.2 –Customisation to the 2 nd domain Evaluation results per partner Relevant section in D3.3 –Customisation methodology

WP3: Plan for the remainder (3) Name matching –Evaluation results per partner –Relevant section in D3.2 –Customisation to the 2 nd domain Evaluation results per partner Relevant section in D3.3 –Customisation methodology

WP3: Plan for the remainder (4) FE v.3 –Application of the 4 techniques (also Lingway’s) to the 2 nd domain Evaluation results per partner –Examine the combination of the 3 techniques (meta-learning) Decide on the strategy, Evaluation results –Customisation methodology Template for relevant section in D3.3 Specify measurements Application in new domains Report per partner Integrated report on a FE customisation methodology –Relevant section in D3.3

WP3: Plan for the remainder (5) Image Segmentation - OCR –Customisation to the 2 nd domain Annotation Evaluation Relevant section in D3.3

WP3: Plan for the remainder (6) IERI + monolingual IE systems –Integration of FE v.2 with NERC v.2 Evaluation of the integrated IE system per language (combination of 3 FE techniques with NERC v.2) Relevant section in D3.2 –Integration of FEv.3 with NERC v.3 Evaluation of the integrated IE system per language (combination of 4 FE techniques with NERC v.3) Relevant section in D3.3 –Modifications to monolingual IE systems to handle runs in more than one domain Relevant section in D3.2

WP3: Plan for the remainder (7) Deliverables –D3.2 Deliver Final version –D3.3 Template Draft Final

WP4: Plan for the remainder (1) End-User Interface –Changes in the UI taking into account the remarks from the evaluation workshops –Report on the UI of the 2 nd prototype in D4.3 –Report on the UI of the Final prototype in D4.4

WP4: Plan for the remainder (2) System Integration –Finalise agents Focused crawling agent, Spidering agent Data Storage agent, Personalisation agent –2 nd integrated prototype Installation & User Manual, Documentation –Final integrated prototype Installation & User Manual, Documentation

WP4: Plan for the remainder (3) Personalisation –Improvements in the final prototype –Stereotypes editor through Protégé –Personalisation methodology –Relevant section in D4.4

WP4: Plan for the remainder (4) Evaluation –Evaluation workshop at RTV –Evaluation report in D4.3 –Final evaluation Finalise evaluation methodology Other evaluation workshops: Where ? When ? Evaluation report in D4.4

WP4: Plan for the remainder (5) Deliverables –D4.3 Deliver Final version –D4.4 Template Draft Final

WP5: Plan for the remainder (1) Management reports –9 th Quarterly Report (deliver end June) –10 th Quarterly Report (deliver mid September) –5 th Semestrial Report, 5 th Cost Statements (deliver mid September) –Final Report (deliver end September)

WP5: Plan for the remainder (3) Dissemination Plan - I –1st European Summer School on Ontological Engineering and the Semantic Web (SSSW-2003), July 21-26, Cercedilla, Spain ( Promote CROSSMARC and invite to a web-based evaluation. –2nd International Workshop on Web Document Analysis (WDA- 2003), August 3, Edinburgh ( Promote CROSSMARC and invite to a web-based evaluation. –Ontologies and Information Extraction International Workshop held as part of the EUROLAN Summer School, July 28 - August 8, 2003, Bucarest, Romania ( Schoolhttp://ic2.epfl.ch/~pallotta/ontoIE/

WP5: Plan for the remainder (4) Dissemination Plan - II –Recent Advances in Natural Language Processing (RANLP-2003), September 2003, Borovets, Bulgaria –8th National Congress of the Italian Association of Artificial Intelligence (AI*IA 2003), September 23-26, Pisa ( aiia2003.di.unipi.it/aiia2003/index-eng.html). Promote CROSSMARC and invite to a web-based evaluation (??). aiia2003.di.unipi.it/aiia2003/index-eng.html –IST-2003, October 4-7, Milan, Italy. Plans to demonstrate CROSSMARC technology through a CROSSMARC exhibition (a relevant proposal has already been submitted). –9th Panhellenic Conference on Informatics, November 21-23, 2003, Thessaloniki (

WP5: Plan for the remainder (5) Dissemination Plan – III –Multilingual CROSSMARC site –Multilingual Questionnaire Technology Implementation Plan –Draft –Final Date and place of final meeting before the review