****Call for applications still open (until March 16, 2007)*****
****Early Registration until April 19, 2007*********************
RIAO 2007 Large-Scale Semantic Access to Content (Text, Image, Video
and Sound)
Pittsburgh, PA, USA, Carnegie Mellon University
May 30 to June 1, 2007
The RIAO (Research of information assisted by computer) conference is
organized
every three years, in Europe and North America, by the Center for
Advanced Study
of Information Systems (CASIS) and the Centre de Hautes Etudes
Internationales
d'Informatique Documentaire (CID). The RIAO conferences present recent
scientific
advances in information retrieval through oral presentations,
posters,
demonstrations of research prototypes as well as presenting a
selection of
cutting-edge innovative products.


Preliminary Conference Program
WEDNESDAY MAY 30, 2007
Wed 8:00-9:00 a.m.              Registration
Wed 9:00-10:00 a.m.             Opening Session
Wed 10:00-10:45 a.m.    Invited Speaker Donna Harman - NIST, USA
Wed 10:45-11:00 a.m.    Break
Wed 11:00-12:15 a.m.    SESSION 1       VIDEO AND LOG RETRIEVAL
Pic-A-Topic: Efficient Viewing of Informative TV Contents on Travel,
Cooking,
Food and More
        Tetsuya Sakai, Toshiba/NewsWatch - Japan, Tatsuya Uehara, Taishi
Shimomori,
        Makoto Koyama, Mika Fukui, Toshiba -  Japan
Multimodal Segmentation of Lifelog Data
        Aiden R. Doherty,  Alan F. Smeaton, CDVP, Dublin City University -
Ireland,
        Keansub Lee, Daniel P.W. Ellis, LabROSA, Columbia University - USA
SportsAnno: What Do You Think?
        James Lanagan, Alan Smeaton, CDVP, Dublin City University -  Ireland

Wed 12:15-01:30 p.m.    Lunch
Wed 1:30-03:10 p.m.             SESSION 2       SOUND AND MUSIC RETRIEVAL
ORCHIVE: Digitizing and Analyzing Orca Vocalizations
        George Tzanetakis, Mathieu Lagrange, University of Victoria -
Canada,
        Paul Spong, Helena Symonds, Orcalab - Canada
Optimizations of Local Edition for Evaluating Similarity Between
Monophonic
Musical Sequences
        Pierre Hanna, Pascal Ferraro, LaBRI, Bordeaux 1 University - France
Multi-Modal Music Information Retrieval - Visualisation and Evaluation
of Clusterings
by Both Audio and Lyrics
        Robert Neumayer, Andreas Rauber, Vienna University of Technology -
Austria
Recent Advances in Automatic Speech Summarization
        Sadaoki Furui, Tokyo Institute of Technology - Japan

Wed 3:10-3:40 p.m.              Break and Demonstrations
Wed 3:40-5:40 p.m.              POSTER SESSION 1
Semantic Domains and Supersense Tagging for Domain-Specific Ontology
Learning
        Davide Picca, University of Lausanne - Switzerland
Unified Access to Heterogeneous Data in Cultural Heritage
        Marijn Koolen, Avi Arampatzis, Jaap Kamps, University of Amsterdam -
Netherlands,
        Vincent de Keijzer, Haags Gemeentemuseum, The Hague -  Netherlands,
        Nir Nussbaum, University of Amsterdam -  Netherlands
An approach to Multi-Lingual Text Summarization
        Alkesh Patel, Tanveer Siddiqui, Umashankar Tiwary,
        University of Allahabad - India
Cross-Media Entity Recognition in Nearly Parallel Visual and Textual
Documents
        Koen Deschacht, Marie-Francine Moens, Wouter Robeyns, Katholieke
        Universiteit Leuven - Belgium
Query Refinement based on Topical Term Clustering
        Hiromi Wakaki, The University of Tokyo - Japan, Tomonari Masada,
Atsuhiro Takasu,
        Jun Adachi, National Institute of Informatics, The University of
Tokyo - Japan
Discriminative Fields for Modeling Semantic Concepts in Video
        Ming-yu Chen, Alexander Hauptmann, Carnegie Mellon University - USA
Multi-modal Interview Concept Detection for Rushes Exploitation
        Anan Liu, Tianjin University, Chinese Academy of Sciences - China,
Li Jintao,
        Zhang Yongdong, Tang Sheng, Academy of Sciences - China, Yang
Zhaoxuan,
        Tianjin University, Chinese Academy of Sciences - China
Query clustering to decide the best system to use
        D$(D??(Bsir$(D??(B Kompaor$(D??(B, IRIT, Toulouse 3 University - France, Josiane Mothe,
IUFM,
        IRIT - France, Alain Baccini, S$(D??(Bbastien Dejean, LSP, Toulouse 3
University - France
An IE and IR Approach to deal with Geographic Information Scope in
Textual Documents
        Christian Sallaberry, LIUPPA, Pau University - France, Mustapha
Baziz, IRIT, Toulouse
        3 University - France, Julien Lesbegueries, Mauro Gaio, LIUPPA, Pau
University - France
Comprehensible and Accurate Cluster Labels in Text Clustering
        Jerzy Stefanowski, Dawid Weiss, Poznan University of Technology -
Poland
Summarizing non-textual events with 'Briefing' focus
        Mohit Kumar, Dipanjan Das, Alexander Rudnicky, Carnegie Mellon
University - USA
A Robust Linguistic Platform for Efficient and Domain specific Web
Content Analysis
        Thierry Hamon, Adeline Nazarenko, Thierry Poibeau, Sophie Aubin,
        Julien Derivi$(D??(Bre, LIPN, Paris 13 University - France
OLAP Dimensions for Multidimensional Document Anlaysis
        Franck Ravat, IRIT, Toulouse 1 University - France, Olivier Teste,
        Ronan Tournier, IRIT, Toulouse 3 University - France
Effectiveness of Rich Document Representation in XML Retrieval
        Fahimeh Raja, Mostafa Keikha, Maseud Rahgozar, University of Teheran
- Iran
        Farhad Oroumchian, University of Wollongong - Dubai
Expanding a Test Collection for Citation-based IR Experiments
        Anna Ritchie, University of Cambridge - UK, Stephen Robertson,
Microsoft Research Ltd UK,
        Simone Teufel, University of Cambridge - UK

Wed 5:40-6:30 p.m.              SESSION 3       TEXTUAL QUERIES AND SEARCH 1
Selecting Automatically the Best Query Translation
        Pierre-Yves Berger, Jacques Savoy, University of Neuchatel -
Switzerland
An Information Retrieval Driven by Ontology: from Query to Document
Expansion
        Mustapha Baziz, Mohand Boughanem, IRIT, Toulouse 3 University -
France,
        Gabriella Pasi, Universit$(D??(B degli Studi di Milano Bicocca - Italy,
        Henri Prade, IRIT, Toulouse 3 University - France
________________________________________
THURSDAY MAY 31, 2007
Thu 9:00-9:45 a.m.      Invited Speaker Alan Smeaton - Dublin City
University, Ireland
Thu 9:45-10:35 a.m.     SESSION 4       TEXTUAL QUERIES AND SEARCH 2
Modeling Information Scent: A Comparison of LSA, PMI and GLSA
Similarity Measures on Common
Tests and Corpora
        Raluca Budiu, Christiaan Royer, Peter Pirolli, Palo Alto Research
Center - USA
Investigating Retrieval Performance with Manually-Built Topic Models
        Xing Wei, W. Bruce Croft, University of Massachusetts Amherst - USA

Thu 10:35-11:00 a.m.    Break and Demonstrations
Thu 11:00-12:40 p.m.    SESSION 5       MODELING LANGUAGE AND SEARCH
Document frequency and term specificity
        Hideo Joho, University of Glasgow - UK, Mark Sanderson, University of
Sheffield - UK
Context Based Word Prediction for Texting Language
        Sachin Agarwal, Shilpa Arora, Carnegie Mellon University - USA
Combining linguistic indexes to improve the performances of
information retrieval systems:
a machine learning based solution
        Fabienne Moreau, Vincent Claveau, Pascale S$(D??(Bbillot, IRISA, Rennes
University - France
Using Markov Chains to Exploit Word Relationships in Information
Retrieval
        Guihong Cao, Jian-Yun Nie, Jing Bai, University of Montreal - Canada

Thu 12:40-1:30 p.m.             Lunch
Thu 1:30-3:30 p.m.              APPLICATIONS SESSION
Thu 3:30-4:00 p.m.              Break and Demonstrations
Thu 4:00-5:15 p.m.              SESSION 6       XML IN RETRIEVAL
A Survey on XML Focussed Component Retrieval
        Karen Pinel-Sauvagnat, Mohand Boughanem, IRIT, Toulouse 3 University
- France
XML Fragments Extended with Database Operators
        Yosi Mass, Dafna Sheinwald, Benjamin Sznajder,
        Sivan Yogev, IBM Research Laboratory in Haifa - Israel
>From Layout to Semantic: a Reranking Model for Mapping Web Documents
to Mediated
XML Representations
        Guillaume Wisniewski, Patrick Gallinari, LIP6, Paris 6 University -
France

Thu 5:15-6:05 p.m.              SESSION 7       IMAGE RETRIEVAL 1
Similarity Beyond Distance Measurement
        Feng Kang, Rong Jin, Michigan State University - USA,
        Steven Hoi, Hong Kong Chinese University - China
Image Retrieval Using a Multilingual Ontology
        Adrian Popescu, CEA LIST - France
________________________________________
FRIDAY JUNE 1, 2007
Fri 9:00-10:40 a.m.             SESSION 8       PEER-TO-PEER AND WEB SEARCH
A Co-operative Web Services Paradigm for Supporting Crawlers
        Aravind Chandramouli, Susan Gauch, University of Kansas - USA
Content-Based Peer-to-Peer Network Overlay for Full-Text Federated
Search
        Jie Lu, Jamie Callan, Carnegie Mellon University - USA
Homepage Finding in Hybrid Peer-to-Peer Networks
        Enrico Bragante, Massimo Melucci, University of Padua - Italy
Collective Annotation: Perspectives for Information Retrieval
Improvement
        Guillaume Cabanac, Max Chevalier, Claude Chrisment, Christine
Julien,
        IRIT, Toulouse 3 University - France

Fri 10:40-11:10 a.m.    Break and Demonstrations
Fri 11:10-12:00 a.m.    SESSION 9       IMAGE RETRIEVAL 2
Toward Content-based Indexing and Retrieval of Functional Brain Images
        Bing Bai, Paul Kantor, Nicu Cornea, Deborah Silver, Rutgers
University - USA
Using the Knowledge of Object Colors to Segment Images and Improve Web
Image Search
        Christophe Millet, CEA LIST - France, Isabelle Bloch, GET-ENST -
France

Fri 12:00-1:00 p.m.             Lunch
Fri 1:00-2:40 p.m.              SESSION 10      LINKS, PRIOR INFORMATION IN SEARCH
Relevance Propagation Model for Large Hypertext Documents Collections
        Idir Chibane, Bich-Lien Doan, SUP$(D??(BLEC - France
Combination of Document Priors in Web Information Retrieval
        Jie Peng, Craig Macdonald, Ben He, Iadh Ounis, University of Glasgow
- UK
Contextual Search Using Ontology-Based User Profiles
        Vishnu Challam, Microsoft Corporation - USA, Susan Gauch,
        Aravind Chandramouli, University of Kansas - USA
Evidence-Based Information Extraction for High Accuracy Citation and
Author Name
Identification
        Brett Powley, Robert Dale, Macquarie University - Australia

Fri 2:40-4:00 p.m.              POSTER SESSION 2
An Emergent Taxonomy Approach For Information Retrieval in Open
Systems
Val$(D??(Brie Camps, Pierre Glize, IRIT, Toulouse 3 University - France
Extracting Useful Information from the Full Text of Fiction
Sharon Givon, Maria Milosavljevic, University of Edinburgh - UK
Ontology-Aided vs. Keyword-Based Web Searches: A Statistical
Comparative Analysis
Magdi Kamel, Ann Lee, Ed Powers, Naval Postgraduate School, Monterey -
USA
Smart Qualitative Data (SQUAD): Information Extraction in a Large
Document Archive
Maria Milosavljevic, Claire Grover, University of Edinburgh - UK,
Louise Corti, University of Essex - UK
Indexing Low Frequency Information for Answering Complex Questions
Abolfazl Keighobadi Lamjiri, Julien Dubuc, Leila Kosseim, Sabine
Bergler, CLaC laboratory, Concordia University - Canada
Using Prior Information Derived from Citations in Literature Search
Edgar Meij, Maarten de Rijke, University of Amsterdam -  Netherlands
Information Retrieval Techniques for Templated Queries
Giridhar Kumaran, James Allan, University of Massachusetts Amherst -
USA
Discovering Missing Values in Semi-Structured Databases
Xing Yi, James Allan, Victor Lavrenko, University of Massachusetts
Amherst - USA
Audio Feature Engineering for Automatic Music Genre Classification
Paolo Annesi, Roberto Basili, Raffaele Gitto, Alessandro Moschitti,
Riccardo Petitti, University of Rome Tor Vergata - Italy
Exploring Interactive Information Retrieval: An Integrated Approach to
Interface Design and Interaction Analysis
Gheorghe Muresan, Rutgers University - USA

Fri 4:00-4:30 p.m.              Break and Demonstrations
Fri 4:30-5:45 p.m.              SESSION 11      QUESTION ANSWERING, FACTS, AND
SUMMARIES
Logical Validation, Answer Merging and Witness Selection - A Study in
Multi-Stream
Question Answering
        Ingo Gl$(D??(Bckner, Sven Hartrumpf, Johannes Leveling, University of Hagen
- Germany
Estimating Importance Features for Fact Mining (With a Case Study in
Biography Mining)
        Sisay Fissaha Adafre, Maarten de Rijke, Informatics Institute,
        University of Amsterdam - Netherlands
Capturing Sentence Prior for Query-Based Multi-Document Summarization
        Prasad Pingali, International Institute of Information Technology -
India,
        Jagadeesh Jagarlamudi, Microsoft - USA
Fri 5:45-6:30 p.m.              Concluding Ceremony