HOME | PROGRAM | REGISTRATION | CALL FOR PAPERS | SPONSOR | LOCAL ARRANGEMENTS | PAST CONFERENCES | CONTACT
Conference Program Overview
Program by Day
Sunday, May 24th
Monday, May 25th
Tuesday, May 26th
Wednesday, May 27th
Workshops
The conference has several co-located workshops including:
- Computer and Robot Vision (CRV 2009) Tutorial Day - A free day of tutorials will be held on Sunday May 24, the day prior to CRV conference. The tutorial day will consist of many short 15-30 minute presentations in areas of interest to CRV attendees. The topics are areas of importance in computer vision and robotics, and specifically on subjects presented in the following days at the conference itself.
- The Second Canadian Semantic Web Working Symposium 2009 - CSWWS 2009 aims at bringing together Canadian and international researchers in semantic technologies and knowledge management to discuss about various issues related to the Semantic Web.
- Canadian AI Graduate Student Symposium - The Symposium provides an opportunity for Master's and PhD students to discuss and explore their research interests and career objectives with their peers and with a panel of established researchers in Artificial Intelligence, helping to develop a supportive community of scholars and a spirit of collaborative research.The symposium is free. Meals are not included. Breakfast and lunch may be purchased on-site.
General Chair:
Yves Lucet,
University of British Columbia, Kelowna, British Columbia, Canada
Location:
University of British Columbia, Okanagan Campus, Kelowna, BC.
>>Campus Map
Final Printed Program
Sunday, May 24, 2009
| Time | AI Graduate Symposium in Art 183 |
CRV Tutorials in Art 104 |
AI Web Semantics Symposium in Art 185 |
||||||
| 8:30- 9:00 |
Breakfast (additional charge for non-presenters/speakers) in Arts 183 |
Tutorial Session 1 |
Breakfast in Arts 185 | ||||||
| 9:00 - 10:30 |
Session 1 Lead Panelist: Howard Hamilton
|
Keynote: Dr. Helen Chen (Agfa Healthcare) Talk title: Research and Innovation for Healthcare Session 1: Semantic Web and Life Sciences (starting at 9:50 a.m.)
|
|||||||
| 10:30 - 10:40 |
Morning Break Poster Presentations in Arts Atrium/Arts Foyer |
||||||||
| 10:40 - 12:00 |
Session 2
|
Tutorial Session 2 |
Session 2: Modular, Distributed and Sub-Ontologies
|
||||||
| 12:00 - 1:30 |
Lunch Break in Workshop Room (Arts 183, 104, or 185) | ||||||||
| 1:30 - 2:30 |
Invited Talk: Fred Popowich The Future of Artificial Intelligence |
Tutorial Session 3 |
|
||||||
| 2:30 - 3:10 |
Session 3 Lead Panelist: Veronica Dahl (until 3:50 p.m.)
|
||||||||
| 3:10 - 3:30 |
Coffee Break 3:10 - 3:30 | ||||||||
| 3:30 - 3:50 |
Tutorial Session 4 |
Session 4 Semantic Web and Knowledge Reasoning
|
|||||||
| 3:50 - 4:00 |
Afternoon Break Poster Presentations in Arts Atrium/Arts Foyer |
||||||||
| 4:00 - 4:10 |
|||||||||
| 4:10 - 4:30 |
Session 4 Lead Panelist: Richard Sutton
|
||||||||
| 4:30 - 5:30 |
Canadian Semantic Web Research Community Open meeting |
||||||||
| 5:30 - 7:00 |
Conference Registration in Arts Foyer | ||||||||
| 7:00 - 8:00 |
Conference Welcome Reception in Arts Atrium |
||||||||
Monday, May 25, 2009
| Time | AI 2009 in Art 386 |
GI 2009 in Art 376 |
CRV 2009 in Art 366 |
||||||||||
| 7:30 - 8:00 |
Breakfast in Sunroom in Student Service Center |
||||||||||||
| 8:00 - 8:30 |
Conference Opening in Art 366 |
||||||||||||
| 8:30 - 9:30 |
Session 1: Machine Learning for Stock Market Prediction, Heuristic Search, and Games
|
|
|
||||||||||
| 9:30 - 10:30 |
Invited Talk: Jonathan Schaeffer Computer (and Human) Perfection at Checkers |
|
|||||||||||
| 10:30 - 11:00 |
Morning Break Poster Presentations (AI,GI,CRV) in Arts Atrium/Arts Foyer |
||||||||||||
| 11:00 - 12:00 |
Session 2: Satisfiability and Knowledge Representation
|
|
|
||||||||||
| 12:00 - 1:15 |
Lunch Break - Sunroom in Student Service Center Poster Presentations (AI,GI,CRV) in Arts Atrium/Arts Foyer |
||||||||||||
| 1:15 - 2:15 |
Session 3: Machine Learning: Classification, Evaluation, Clustering
|
Invited Talk: David Luebke NVIDIA Research Graphics Hardware & GPU Computing: Past, Present, and Future |
|
||||||||||
| 2:15 - 3:15 |
| Invited Talk: Jim Little University of British Columbia Vision for Robots at Home and at Work |
|||||||||||
| 3:15 - 3:45 |
Afternoon Break Poster Presentations (AI,GI,CRV) in Arts Atrium/Arts Foyer |
||||||||||||
| 3:45 - 4:45 |
Session 4: Text Mining
|
|
|
||||||||||
| 5:00 - 9:00 |
Kelowna Tours Summerhill Pyramid Winery Okanagan Princess Boat Tour |
||||||||||||
Tuesday, May 26, 2009
| Time | AI 2009 in Art 386 |
GI 2009 in Art 376 |
CRV 2009 in Art 366 |
|||||
| 7:30 - 8:30 |
Breakfast in Sunroom in Student Service Center |
|||||||
| 8:30 - 10:15 |
Conference Plenary in Art 366 |
|||||||
| 10:15 - 11:00 |
Morning Break Poster Presentations (AI,GI,CRV) in Arts Atrium/Arts Foyer |
|||||||
| 11:00 - 12:00 |
Session 5: NLP: Machine Translation
|
|
Invited Talk: Rui Castro Columbia University Learning to Learn: Closing the Loop Between Data Analysis and Acquisition |
|||||
| 12:00 - 1:30 |
Lunch Break - Sunroom in Student Service Center | |||||||
| 1:30 - 2:30 |
Invited Talk: Evgeniy Gabrilovich AI in Web advertising: picking the right ad ten thousand times a second |
|
|
|||||
| 2:30 - 3:30 |
Session 6: Web Technologies and Text Mining
|
CHCCS Achievement Award: Przemyslaw Prusinkiewicz University of Calgary Images of life: How visual computing is shaping plant biology |
|
|||||
| 3:30 - 4:00 |
Afternoon Break Poster Presentations (AI,GI,CRV) in Arts Atrium/Arts Foyer Poster tear down starting at 4 p.m. and must be completed by 5 p.m. |
|||||||
| 4:00 - 5:00 |
CAIAC meeting |
CHCCS meeting |
CIPPRS meeting |
|||||
| 5:00 - 5:30 |
CAIAC Precarn Intelligent Systems Challenge Awards Ceremony in Sunroom |
|||||||
| 5:30 - 7:00 |
Awards Reception Sunroom in Student Service Center |
|||||||
| 7:00 - 9:00 |
Award Banquet (AI/GI/CRV 2009) Sunroom in Student Service Center |
|||||||
Wednesday, May 27, 2009
| Time | AI 2009 in Art 386 |
GI 2009 in Art 376 |
CRV 2009 in Art 366 |
|||||||||||
| 8:00 - 8:30 |
Breakfast in Sunroom in Student Service Center |
|||||||||||||
| 8:30 - 9:30 |
Session 7: Machine Learning: Decision Trees, Bayesian Learning
|
|
Invited Talk: Ben Kimia Brown University Shapes and Shock Graphs: From Segmented Shapes to Shapes Embedded in Images |
|||||||||||
| 9:30 - 10:30 |
Session 8: NLP: Word Segmentation, Parsing
|
|
||||||||||||
| 10:30 - 11:00 |
Morning Break in Art Foyer | |||||||||||||
| 11:00 - 12:00 |
Session 9: NLP
|
|
|
|||||||||||
| 12:00 - 1:00 |
Lunch Break - Sunroom in Student Service Center / Steering Committee Meeting (till 2pm) | |||||||||||||
| 1:00 - 2:00 |
Invited Talk: Alan Mackworth Living with Constraints |
|
|
|||||||||||
| 2:00 - 3:00 |
Session 10: Constraint Satisfaction
|
Invited Talk: Vidya Setlur Nokia Research Center Semantic Graphics for More Effective Visual Communication |
||||||||||||
| 3:00 - 3:30 |
Afternoon Break in Arts Foyer | |||||||||||||
| 3:30 - 4:30 |
Session 11: NLP: Sentiment Analysis, Recommender Systems
|
|
||||||||||||
Conference Plenary
Network for Effective Collaboration Technologies through Advanced Research (NECTAR)
A Report on Five Years worth of Achievement
Panel Members:
Associate Director and Moderator:
Professor Kellogg Booth, University of British Columbia
Theme Leaders:
Theme 1: Professor Saul Greenberg, University of Calgary
Theme 2: Professor Carl Gutwin, University of Saskatchewan
Theme 3: Professor Ron Baecker, University of Toronto, and NECTAR PI
NECTAR, a NSERC network of some of Canada's leading researchers in human-computer interaction (HCI) and Computer Supported Cooperative Work (CSCW), consists of members from 6 universities across Canada; University of Toronto, University of British Columbia, University of Saskatchewan, University of Calgary, Queen's University and Dalhousie University.
It was awarded Cdn. $5.5M in research funds from NSERC with additional support from industry sponsors, most notably Smart Technologies and Microsoft. Over the past five years more than 200 professors, students and postdocs have participated in NECTAR research and contributed to over 500 publications. Several have also spun off successful technologies and companies.
Focusing on collaborative technologies, NECTAR has concentrated on the investigation of technological and social issues to make computer-supported collaboration more efficient, more productive and more natural. The work has centered around three specific themes:
- Theme 1 - A Virtual Commons - Using Awareness to Move into Collaboration
Researching and articulating how people maintain awareness of others and of communal events and artifacts, and how people use that awareness to initiate collaboration in both real-world and computerized environments. - Theme 2 - High-Performance Workrooms - Interaction with Shared Displays and Workspaces
Developing a detailed understanding of how people interact over real-world surfaces, and of the limitations imposed by current computational displays and workspaces. - Theme 3 - The Extended Presentation Room - Scalable Interactive Audiovisual Communications
Providing groups with a flexible and scalable technology that manages presentations to both small and large groups in real-time and retrospectively, and that engages all participants and allows them to interact.
The Theme Leaders will report on achievement of their respective Themes providing details of related research and tech transfer that has taken place over the five year duration of NECTAR. Challenges for the future will also be stressed.
Invited Speakers - AI
Computer (and Human) Perfection at Checkers
Jonathan Schaeffer
University of Alberta
In 1989 the Chinook project began with the goal of winning the human World Checkers Championship. There was an imposing obstacle to success -the human champion, Marion Tinsley. Tinsley was as close to perfection at the game as was humanly possible. To be better than Tinsley meant that the computer had to be perfect. In effect, one had to solve checkers. Little did we know that our quest would take 18 years to complete. What started out as a research project quickly became a personal quest and an emotional roller coaster. In this talk, the creator of Chinook tells the story of the quest for computer perfection at the game of checkers.
Living with Constraints
Alan K. Mackworth
University of British Columbia
In order to thrive, an agent must satisfy dynamic constraints deriving from four sources: its internal structure, its goals and preferences, its external environment and the coupling between its internal and external worlds. The life of any agent who does not respect those constraints will be out of balance. Based on this framing of the problem of agent design, I shall give four perspectives on the theme of living with constraints, beginning with a theory of constraint-based agent design and a corresponding experiment in robot architecture. Second, I shall touch briefly on a personal historical note, having lived with the evolving concept of the pivotal role of constraints throughout my research life.
Third, I shall outline our work on the design of two assistive technology prototypes for people with physical and mental disabilities, who are living with significant additional constraints. Finally, I shall suggest our collective failure to recognize, satisfy and live with various constraints could explain why many of the worlds we live in seem to be out of kilter. This approach hints at ways to restore the balance. Some of the work discussed is joint with Jim Little, Alex Mihailidis, Pinar Muyan-Ozcelik, Robert St-Aubin, Pooja Viswanathan, Suling Yang, and Ying Zhang.
AI in Web advertising: picking the right ad ten thousand times a second
Evgeniy Gabrilovich
Research Scientist and Manager of the NLP & IR Group at Yahoo! Research
Online advertising is the primary economic force behind many Internet services ranging from major Web search engines to obscure blogs. A successful advertising campaign should be integral to the user experience and relevant to their information needs as well as economically worthwhile to the advertiser and the publisher. This talk will cover some of the methods and challenges of computational advertising, a new scientific discipline that studies advertising on the Internet. At first approximation, and ignoring the economic factors above, finding user-relevant ads can be reduced to conventional information retrieval.
However, since both queries and ads are quite short, it is essential to augment the matching process with external knowledge. We demonstrate how to enrich query representation using Web search results, and thus use the Web as a repository of relevant query-specific knowledge. We will discuss how computational advertising benefits from research in many AI areas such as machine learning, machine translation, and text summarization, and also survey some of the new problems it poses in natural language generation, named entity recognition, and user modeling.
Invited Speakers - CRV
Vision for Robots at Home and at Work
Jim Little
University of British Columbia
Increasingly we want computers and robots to observe us and know who we are and what we are doing, and to understand the objects and tasks in our world, both at work and at home. I will describe how we've built systems for mobile robots to find objects using visual cues and how a range of visual capabilities permits the robot to work for and with humans.
Learning to Learn: Closing the Loop Between Data Analysis and Acquisition
Rui Castro
Columbia University
In this talk I present a discussion of active learning, or learning using sequential experimental designs. In many practical scenarios it is possible to adjust the data collection process based on information gleaned from previous observations, in the spirit of the "twenty-questions" game. These techniques, generically referred to as active learning or adaptive sampling, have the potential to dramatically improve the learning performance. Although appealing, analysis of such procedures is difficult, due to the complicated dependencies in the data created by the closed-loop observation process. These difficulties are further exasperated by the presence of measurement uncertainty or noise.
In this talk I present a quantitative analysis of active learning in a variety of scenarios, in particular I present results characterizing the fundamental limits of active learning for set estimation in nonparametric settings. I will also present a novel active sensing procedure - Distilled Sensing - that is effective for the detection and estimation of high-dimensional sparse signals in noise. Large-sample analysis shows that the proposed procedure provably outperforms the best possible detection methods based on non-adaptive sensing, allowing for the detection and estimation of extremely weak signals.
Shapes and Shock Graphs: From Segmented Shapes to Shapes Embedded in Images
Ben Kimia
Brown University
The recognition of shapes in figure-ground segmented images is challenging due to the tremendous range of variations caused by changes in viewpoint, object pose, illumination, articulation, occlusion, and most significantly within category variations. The key to successful recognition is the use of a representation whose topology captures this variation, so that in general small changes in shape cause small changes to the representation, and to explicitly deal with cases when this is violated.
This talk will show how the the shock graph representation of shape is a suitable intermediate representation in mediating the pixel-bound intensities and coordinate-free object models. We show two approaches, one for bottom-up perceptual grouping and object recognition, and one in model-based object recognition and segmentation, both using a notion of object fragments induced by the shock graph.
Invited Speakers - GI
Graphics Hardware & GPU Computing: Past, Present, and Future
David Luebke
NVIDIA Research
Modern GPUs have emerged as the world's most successful parallel architecture. GPUs provide a level of massively parallel computation that was once the preserve of supercomputers like the MasPar and Connection Machine. For example, NVIDIA's GeForce GTX 280 is a fully programmable, massively multithreaded chip with up to 240 cores, 30,720 threads and capable of performing up to a trillion operations per second. The raw computational horsepower of these chips has expanded their reach well beyond graphics. Today's GPUs not only render video game frames, they also accelerate physics computations, video transcoding, image processing, astrophysics, protein folding, seismic exploration, computational finance, radioastronomy - the list goes on and on. Enabled by platforms like the CUDA architecture, which provides a scalable programming model, researchers across science and engineering are accelerating applications in their discipline by up to two orders of magnitude. These success stories, and the tremendous scientific and market opportunities they open up, imply a new and diverse set of workloads that in turn carry implications for the evolution of future GPU architectures. In this talk I will discuss the evolution of GPUs from fixed-function graphics accelerators to general-purpose massively parallel processors. I will briefly motivate GPU computing and explore the transition it represents in massively parallel computing: from the domain of supercomputers to that of commodity "manycore" hardware available to all. I will discuss the goals, implications, and key abstractions of the CUDA architecture. Finally I will close with a discussion of future workloads in games, high-performance computing, and consumer applications, and their implications for future GPU architectures.
Semantic Graphics for More Effective Visual Communication
Vidya Sutler
Nokia Research Center
Computers are becoming faster, smaller and more interconnected, creating a shift in their primary function from computation to communication. This trend is exemplified by ubiquitous devices such as mobile phones with cameras, personal digital assistants with video, and information displays in automobiles. As communication devices and viewing situations become more plentiful, we need imagery that facilitates visual communication across a wide range of display devices. In addition, producing effective and expressive visual content currently requires considerable artistic skill and can consume days. There is a growing need to develop new techniques and user interfaces that enhance visual communication, while making it fast and easy to generate compelling content. New algorithms in semantic graphics, i.e. combining concepts and methods from visual art, perceptual psychology, information processing, and cognitive science, help facilitate users in creating, understanding and interpreting computer imagery. In this talk, Vidya Setlur will present the usage of semantic graphics for various information visualization goals.
Images of life: How visual computing is shaping plant biology
Przemyslaw Prusinkiewicz
University of Calgary
In recent years, the use of sophisticated imaging techniques for acquiring
and processing microscopic data, combined with visual computational models
and simulations, has revolutionized developmental biology of plants.
Genetic techniques make it possible to visualize and track tagged
molecules in living cells and tissues. These data are used to construct,
analyze and validate computational models, simulations and visualizations
that capture postulated mechanisms of growth and development. The synergy
between computing and biology results in the advancement of both areas:
development of new computational methods motivated by biological problems,
and emerging integrated, in-depth understanding of the mechanism that
govern the development of patterns and forms in living organisms. This
talk will focus on phyllotaxis, the regular arrangement of plant organs
around their supporting stems that underlies the beauty of flowers, to
illustrate this synergy.
Poster Sessions
CRV - Poster Session #1 (Monday)
- A Robot Control and Augmented Reality Interface for Multiple Robots
Mark Fiala - Canine Pose Estimation: A Computing for Public Safety Solution
Cristina Ribeiro, Alexander Ferworn, Mieso Denko, Jimmy Tran - A Generic Moment Invariants Based Supervised Learning Framework for Classification Using Partial Object Information
Rashid Minhas, Abdul Adeel Mohammed, Q.M. Jonathan Wu - Probabilistic 3D Tracking: Rollator Users' Leg Pose from Coronal Images
Samantha Ng, Adel Fakih, AdamFourney, Pascal Poupart, John Zelek - A Bayesian Algorithm for Reading 1-D Barcodes
Ender Tekin, James Coughlan - Face Classification Using Gabor Wavelets and Random Forest
Vidyut Ghosal, Paras Tikmani, Phalguni Gupta - Video Pause Detection using Wavelet
Shiva Zaboli, David A. Clausi - Near-Real-Time Image Matting with Known Background
Minglun Gong, Yee-Hong Yang - Motion Histogram Analysis Based Key Frame Extraction for Human Action/Activity Representation
Ling Shao, Ling Ji - Towards Navigation Summaries: Automated Production of a Synopsis
G. Dudek, J.P. Lobos
CRV - Poster Session #2 (Tuesday)
- A Segment and Fusion Based Stereo Approach
Frank Pagel - IceSynth: An Image Synthesis System for Sea-Ice Segmentation Evaluation
Alexander Wong, Wen Zhang, David A. Clausi - AI Goggles: Real-time Description and Retrieval in the RealWorld with Online Learning
Hideki Nakayama, Tatsuya Harada, Yasuo Kuniyoshi - A Support Vector Machine Based Online Learning Approach for Automated Visual Inspection
Jun Sun, Qiao Sun - On the Use of Ray-tracing for Viewpoint Interpolation in Panoramic Imagery
Feng Shi, Robert Laganiere, Eric Dubois, Frederic Labrosse - An Efficient Local Invariant Region Detector for Image Retrieval
Ling Shao - Robust Monocular Egomotion Estimation Based on an IEKF
Frank Pagel - A Stereo-Based System with Inertial Navigation for Outdoor 3D Scanning
Tomasz Byczkowski, Jochen Lang - Towards Learning Robotic Reaching and Pointing: An Uncalibrated Visual Servoing Approach
Azad Shademan, Amir-massoud Farahmand, Martin Jagersand - Robust 3D Spatio-Temporal Interest Point Detection For Human Action Recognition
Hossein Shabani, David A. Clausi, John S. Zelek - Efficient Online Egomotion Estimation using Visual and Inertial Readings
Raphael Mannadiar - 3D Modeling from Multiple Views with Integrated Registration and Data Fusion
Alain Boyer, Phillip Curtis, Pierre Payeur
GI Posters
- Projected Fishtank Virtual Reality for Architectural Models
Russell MacKenzie, Kellogg S. Booth, Kirstie Hawkey, Sheryl Staub-French - Lacome: The Large Collaborative Meeting Environment
Russell MacKenzie, Zhangbo Liu, Presley Perswain, Kirstie Hawkey, Kellogg S. Booth - Whale Tank Virtual Reality: Collaboration in VR Using a Large Screen
Evgeny Maksakov, Kirstie Hawkey, Kellogg S. Booth - Graphically-Enhanced Keyboard Accelerators
Jeff Hendy, Joanna McGrenere, Kellogg S. Booth - The Benefits of Thumbnails for Browsing of Search Engine Results
Daniel Natapov - A Shadow Culling Algorithm for Interactive Ray Tracing
Jae-ho Nah, Kyung-ho Lee, Woo-chan Park, Tack-don Han
AI - Poster Session #1 (Monday)
- Automatic Extraction of Lexical Relations from Definitional Contexts IS-A Using a Constraint Grammar
Olga Acosta - Grid-Enabled Adaptive Metamodeling and Active Learning for Computer Based Design
Dirk Gorissen - Reasoning About Movement in Two-Dimensions
Joshua Gross - Executable Specifications of Fully General Attribute Grammars with Ambiguity and Left-recursion
Rahmatullah Hafiz - K-MORPH: A Semantic Web Based Knowledge Representation and Context-driven Morphing Framework
Sajjad Hussain - Background Knowledge Enriched Data Mining for Interactome Analysis
Mikhail Jiline - Modeling and Inference with Relational Dynamic Bayesian Networks
Cristina Manfredotti - A Semi-supervised approach to Bengali-English Phrase-based Statistical Machine Translation
Maxim Roy - Machine Translation of Legal Information and its Evaluation
Atefeh Farzindar,Guy Lapalme - Enhancing the Bilingual Concordancer TransSearch with Word-level Alignment
Julien Bourdaillet, Fabrizio Gotti, Stéphane Huet, Philippe Langlais, Guy Lapalme - Context Dependent Movie Recommendations
Daniel Pomerantz, Gregory Dudek - Cost-based Sampling of Individual Instances
William Klement, Peter Flach, Nathalie Japkowicz, Stan Matwin - Financial Forecasting using Character N-Gram Analysis and Readability Scores of Annual Reports
Matthew Butler, Vlado Keselj - Automatic Frame Extraction from Sentences
Martin Scaiano, Diana Inkpen - Large Neighborhood Search using Constraint Satisfaction Techniques in Vehicle Routing Problem
Lee Hyun-jin, Cha Sang-jin, Yu Young-hoon, Jo Geun-sik - Belief Rough Set Classifier
Salsabil Trabelsi, Zied Elouedi, Pawan Lingras - A SVM-Based Ensemble Approach to Multi-Document Summarization
Yllias Chali, Sadid Hasan, Shafiq Joty - Classifying Biomedical Abstracts Using Committees of Classifiers and Collective Ranking Techniques
Alexandre Kouznetsov, Stan Matwin, Diana Inkpen, Amir Razavi, Oana Frunza, Morvarid Sehatkar, Leanne Seaward
AI - Poster Session #2 (Tuesday)
- Training Global Linear Models for Chinese Word Segmentation
Dong Song, Anoop Sarkar - Rank-Based Transformation in Measuring Semantic Relatedness
Bartosz Broda, Maciej Piasecki, Stan Szpakowicz - The Role of Operation Granularity in Search-Based Learning of Latent Tree Models
Nevin L. Zhang, Tao Chen, Yi Wang - Improving Document Search Using Social Bookmarking
Hamidreza Baghi, Yevgen Biletskiy - How to Learn Opinion without Using Emotional Words: It is in the Details
Marina Sokolova, Guy Lapalme - An Empirical Study of Category Skew on Feature Selection for Text Categorization
Mondelle Simeon, Robert Hilderman - The WordNet Weaver: Multi-criteria Voting for Semi-automatic Extension of a Wordnet
Maciej Piasecki, Bartosz Broda, Maria Glabska, Michal Marcinczuk, Stan Szpakowicz - Active Learning with Automatic Soft Labeling for Induction of Decision Trees
Jiang Su, Stan Matwin, Jelber Sayyad Shirabad, Jin Huang - Evaluation Methods for Ordinal Classification
Lisa Gaudette, Nathalie Japkowicz - An Ontology-Based Spatial Clustering Selection System
Wei Gu, Xin Wang, Danielle Ziébelin - Optimizing a Pseudo Financial Factor Model with Support Vector Machines and Genetic Programming
Matthew Butler, Vlado Keselj - Novice-Friendly Natural Language Generation Template Authoring Environment
Maria Fernanda Caropreso, Diana Inkpen, Shahzad Khan, Fazel Keshtkar - Valuable Change Detection in Keyword Map Animation
Takuya Nishikido, Wataru Sunayama, Yoko Nishihara - A Procedural Planning System for Goal Oriented Agents in Games
Yingying She, Peter Grogono - Exploratory Analysis of Co-Change Graphs for Code Refactoring
Hassan Khosravi, Recep Çolak - Supervised Learning of Online Handwritten Arabic Characters Using Contextual Information
Sara Izadi - STFLS: A Heuristic Method for Static and Transportation Facility Location Allocation in Large Spatial Datasets
Wei Gu, Xin Wang, Liqiang Geng - Co-Training on Handwritten Digit Recognition
Jun Du, Charles Ling
AI Graduate Symposium Poster Session (Sunday)
- Automatic Extraction of Lexical Relations from Definitional Contexts IS-A Using a Constraint Grammar
Olga Acosta, National Autonomous University of Mexico - Grid-Enabled Adaptive Metamodeling and Active Learning for Computer Based Design
Dirk Gorissen, Ghent University - Reasoning About Movement in Two-Dimensions
Joshua Gross, Ryerson University - Executable Specifications of Fully General Attribute Grammars with Ambiguity and Left-recursion
Rahmatullah Hafiz, Windsor University - K-MORPH: A Semantic Web Based Knowledge Representation and Context-driven Morphing Framework
Sajjad Hussain, Dalhousie University - Background Knowledge Enriched Data Mining for Interactome Analysis
Mikhail Jiline, University of Ottawa - Modeling and Inference with Relational Dynamic Bayesian Networks
Cristina Manfredotti, University of Milano - A Semi-supervised approach to Bengali-English Phrase-based Statistical Machine Translation
Maxim Roy, Simon Fraser University