Edinburg March 2001CROSSMARC Kick-off meetingICDC ICDC background and know-how and expectations from CROSSMARC CROSSMARC Project IST-2000-25366 Kick-off.

Slides:



Advertisements
Similar presentations
Data Mining and the Web Susan Dumais Microsoft Research KDD97 Panel - Aug 17, 1997.
Advertisements

GMD German National Research Center for Information Technology Darmstadt University of Technology Perspectives and Priorities for Digital Libraries Research.
Haystack: Per-User Information Environment 1999 Conference on Information and Knowledge Management Eytan Adar et al Presented by Xiao Hu CS491CXZ.
© 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.
Stefania Bergamasco, Cecilia Colasanti An integrated approach to turn statistics into knowledge combining data warehouse, controlled vocabularies and advanced.
A Java Architecture for the Internet of Things Noel Poore, Architect Pete St. Pierre, Product Manager Java Platform Group, Internet of Things September.
IN350 Document Management & Information Steering Introduction to Document Management. Class 1 August 25, 2003 Judith A. Molka-Danielsen
Effective Coordination of Multiple Intelligent Agents for Command and Control The Robotics Institute Carnegie Mellon University PI: Katia Sycara
Information Retrieval in Practice
Search Engines and Information Retrieval
CS652 Spring 2004 Summary. Course Objectives  Learn how to extract, structure, and integrate Web information  Learn what the Semantic Web is  Learn.
April 22, Text Mining: Finding Nuggets in Mountains of Textual Data Jochen Doerre, Peter Gerstl, Roland Seiffert IBM Germany, August 1999 Presenter:
Semantic Web and Web Mining: Networking with Industry and Academia İsmail Hakkı Toroslu IST EVENT 2006.
Building an Intelligent Web: Theory and Practice Pawan Lingras Saint Mary’s University Rajendra Akerkar American University of Armenia and SIBER, India.
EMNLP Industry Panel Comments © 2001, David A. Evans, Clairvoyance Corporation 1June 4, 2001 The Rubber and the Road Industrial Perspectives on NLP EMNLP.
Enhance legal retrieval applications with an automatically induced knowledge base Ka Kan Lo.
Semantic Web and Web Mining: Networking with Industry and Academia İsmail Hakkı Toroslu IST EVENT 2006.
Overview of Web Data Mining and Applications Part I
Overview of Search Engines
LLNL-PRES This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344.
Xpantrac connection with IDEAL Sloane Neidig, Samantha Johnson, David Cabrera, Erika Hoffman CS /6/2014.
1 Introduction to Web Development. Web Basics The Web consists of computers on the Internet connected to each other in a specific way Used in all levels.
AQUAINT Kickoff Meeting – December 2001 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
Deduplication CSCI 572: Information Retrieval and Search Engines Summer 2010.
Intelligent Systems Lecture 23 Introduction to Intelligent Data Analysis (IDA). Example of system for Data Analyzing based on neural networks.
CS598CXZ Course Summary ChengXiang Zhai Department of Computer Science University of Illinois, Urbana-Champaign.
Challenges in Information Retrieval and Language Modeling Michael Shepherd Dalhousie University Halifax, NS Canada.
1 BTEC HNC Systems Support Castle College 2007/8 Systems Analysis Lecture 9 Introduction to Design.
Search Engines and Information Retrieval Chapter 1.
Survey of Semantic Annotation Platforms
TWIRL Twinning virtual World (on- line) Information with Real world (off-Line) data sources Kick-Off Meeting Cassidian 08 & 09 October 2012, Paris - France.
FIIT STU Bratislava Classification and automatic concept map creation in eLearning environment Karol Furdík 1, Ján Paralič 1, Pavel Smrž.
Center-to-Peer-to-Center A model for building maximal value from peer services.
Master Thesis Defense Jan Fiedler 04/17/98
MinorThird 서울시립대학교 인공지능연구실 곽별샘
Internet Information Retrieval Sun Wu. Course Goal To learn the basic concepts and techniques of internet search engines –How to use and evaluate search.
Use of Hierarchical Keywords for Easy Data Management on HUBzero HUBbub Conference 2013 September 6 th, 2013 Gaurav Nanda, Jonathan Tan, Peter Auyeung,
Web Services and Application of Multi-Agent Paradigm for DL Yueyu Fu & Javed Mostafa School of Library and Information Science Indiana University, Bloomington.
Future Learning Landscapes Yvan Peter – Université Lille 1 Serge Garlatti – Telecom Bretagne.
Search Engines. Search Strategies Define the search topic(s) and break it down into its component parts What terms, words or phrases do you use to describe.
1 Automatic Classification of Bookmarked Web Pages Chris Staff Second Talk February 2007.
October 2005CSA3180 NLP1 CSA3180 Natural Language Processing Introduction and Course Overview.
Project Overview Vangelis Karkaletsis NCSR “Demokritos” Frascati, July 17, 2002 (IST )
Research Topics/Areas. Adapting search to Users Advertising and ad targeting Aggregation of Results Community and Context Aware Search Community-based.
© 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.
Data and Applications Security Developments and Directions Dr. Bhavani Thuraisingham The University of Texas at Dallas Lecture #15 Secure Multimedia Data.
ICT-enabled Agricultural Science for Development Scenarios, Opportunities, Issues by ICTs transforming agricultural science, research & technology generation.
Abstract A Structured Approach for Modular Design: A Plug and Play Middleware for Sensory Modules, Actuation Platforms, Task Descriptions and Implementations.
Internet and Intranet Protocols and Applications Lecture 5a: HTTP Client-Server Design and Implementation February 15, 2005 Arthur Goldberg Computer Science.
Digital Libraries1 David Rashty. Digital Libraries2 “A library is an arsenal of liberty” Anonymous.
NCSR “Demokritos” Institute of Informatics & Telecommunications CROSSMARC CROSS-lingual Multi Agent Retail Comparison Costas Spyropoulos & Vangelis Karkaletsis.
Intelligent Agents. 2 What is an Agent? The main point about agents is they are autonomous: capable of acting independently, exhibiting control over their.
NATURAL LANGUAGE PROCESSING Zachary McNellis. Overview  Background  Areas of NLP  How it works?  Future of NLP  References.
Co-funded by the European Union Semantic CMS Community Reference Architecture for Semantic CMS Copyright IKS Consortium 1 Lecturer Organization Date of.
Usability Lab 2002 Cascade Kick-Off Meeting User Requirements - Web Site Design Multimedia Interface to Material Databases Flavio Fontana (Ulab)
Text Information Management ChengXiang Zhai, Tao Tao, Xuehua Shen, Hui Fang, Azadeh Shakery, Jing Jiang.
AQUAINT Mid-Year PI Meeting – June 2002 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
WP1: Plan for the remainder (1) Ontology –Finalise ontology and lexicons for the 2 nd domain (RTV) Changes agreed in Heraklion –Improvement to existing.
Using Human Language Technology for Automatic Annotation and Indexing of Digital Library Content Kalina Bontcheva, Diana Maynard, Hamish Cunningham, Horacio.
NCSR “Demokritos” Institute of Informatics & Telecommunications CROSSMARC CROSS-lingual Multi Agent Retail Comparison WP3 Multilingual and Multimedia Fact.
Data mining in web applications
Siemens Enables Digitalization: Data Analytics & Artificial Intelligence Dr. Mike Roshchin, CT RDA BAM.
Institute of Informatics & Telecommunications NCSR “Demokritos”
Pipeline Execution Environment
Kenneth Baclawski et. al. PSB /11/7 Sa-Im Shin
Discovering User Access Patterns on the World-Wide Web
Web Engineering.
CSE 635 Multimedia Information Retrieval
AGMLAB Information Technologies
Jana Diesner, PhD Associate Professor, UIUC
Presentation transcript:

Edinburg March 2001CROSSMARC Kick-off meetingICDC ICDC background and know-how and expectations from CROSSMARC CROSSMARC Project IST Kick-off meeting Edinburg March 2001

CROSSMARC Kick-off meetingICDC NLP-based applications at ICDC Documents filtering –Syntactic analysis + NERC + Inference engine –Intranet and commercial internet Documents clustering –Statistical analysis Real-time documents indexing – Search engine techniques

Edinburg March 2001CROSSMARC Kick-off meetingICDC NLP- based prototypes at ICDC Shareholding events detection –Information extraction Documents filtering –transducers (CORAIL) –neural networks (TREC) Control techniques using machine learning –controlling filters with neural networks (RIAO) –controlling NERC with C4.5 (ADIET with NCSR)

Edinburg March 2001CROSSMARC Kick-off meetingICDC NLP-based applications Complex applications –development –exploitation –maintenance Heterogeneous modules –implementation: OS, language, communication, format –processing: data, resources, algorithms

Edinburg March 2001CROSSMARC Kick-off meetingICDC TalLab ICDC architecture for NLP-based applications –Operational since 1997 –Used in several applications and prototypes Publications –[Wolinski et al. 98] NLP+IA, Moncton –[Wolinski et Vichot 01] TSI, Paris Reference –[Cunningham et al. 00] LREC, Athens

Edinburg March 2001CROSSMARC Kick-off meetingICDC Guidelines for the design of TalLab Relying on a multi-agents model Reusing the OS wherever it is possible Refusing to impose a single standard

Edinburg March 2001CROSSMARC Kick-off meetingICDC Agents and circuits in TalLab messagesknowledge Accointances activity behavior persistence message box Agent Circuit of agents

Edinburg March 2001CROSSMARC Kick-off meetingICDC NLP techniques used in TalLab Tokenisation POS tagging Syntactic analysis Named Entity Recognition and Classification Semantic analysis Search engines Neural networks Finite state transducers Vector space model Statistical clustering

Edinburg March 2001CROSSMARC Kick-off meetingICDC Transistor-like agents Cardinality 1-N Cardinality N-1 Cardinality 1-1 Multiplier Dispatcher Switcher Filter TranslatorNetworker ConcentratorSynchronizer

Edinburg March 2001CROSSMARC Kick-off meetingICDC TalLab main features Malleability : plug & play architecture, easy prototyping Openness : reuse market components, low integration cost Efficiency: distribute applications, real-time, batch processing Exploitability: –Deployability full integration in the MIS –Reliability quality of service, robustness –Controllability monitoring facilities, surveillance tools

Edinburg March 2001CROSSMARC Kick-off meetingICDC Malleability Units of production = Circuits of agents Linking modules = Plugging agents

Edinburg March 2001CROSSMARC Kick-off meetingICDC Openness Integrating a component = Building a transducer Managing heterogeneity = Programming a translator

Edinburg March 2001CROSSMARC Kick-off meetingICDC Efficiency Pipeline architectureConcurrent architecture = Using multiplier

Edinburg March 2001CROSSMARC Kick-off meetingICDC Exploitability Deployability –distribution: sub-networks architecture –networkers: intranet proxies and internet firewalls Fiability –modularity: independence of agents –persistence: knowledge / message box / failures Controllability –uniformity: general controlling procedures –OS integration: connection to monitoring software

Edinburg March 2001CROSSMARC Kick-off meetingICDC ICDC technical expectations Adaptive techniques for information extraction from web pages Techniques for managing multilingual NLP- based applications Processing typical web texts (vs news items)

Edinburg March 2001CROSSMARC Kick-off meetingICDC ICDC applicative expectations Evaluation of the added-value of CROSSMARC in the context of CDC Exploitation of CROSSMARC by-products for competitive intelligence applications

Edinburg March 2001CROSSMARC Kick-off meetingICDC Intranet application at CDC Real-time news filtering and clustering –100 users, 100 topics Information retrieval –2 years of AFP economic news

Edinburg March 2001CROSSMARC Kick-off meetingICDC Internet application at CDC-Mercure Real-time news filtering –8,000 users, 80 topics

Edinburg March 2001CROSSMARC Kick-off meetingICDC IE prototype at CDC IE dedicated to shareholding events