Artificial Intelligence and Cognitive Science: 13th Irish International Conference, AICS 2002, Limerick, Ireland, September 12-13, 2002. Proceedings (Lecture ... / Lecture Notes in Artificial Intelligence)

This book constitutes the refereed proceedings of the 13th Irish International Conference on Artificial Intelligence and Cognitive Science, AICS 2002, held in Limerick, Ireland in September 2002. The 16 revised full papers and 17 revised short papers presented were carefully reviewed and selected for inclusion in the book. Among the topics addressed are cognitive modeling, case-based reasoning, constraint processing, data mining, evolutionary computation, intelligent agents, information retrieval, knowledge representation, reasoning, machine learning, natural language processing, neural networks, perception, AI planning, robotics, and scheduling. On the Usefulness of Extracting Syntactic Dependencies for Text Indexing....Pages 3-11 Using Latent Semantic Indexing as a Measure of Conceptual Association for Noun Compound Disambiguation....Pages 12-19 RADAR: Finding Analogies Using Attributes of Structure....Pages 20-27 Classifying Languages Based on Speech Rhythm....Pages 28-35 Finding Agents in a Two-Dimensional Boolean STaM....Pages 36-44 Neuro-symbolic System for Forecasting Red Tides....Pages 45-52 Improved Learning for Hidden Markov Models Using Penalized Training....Pages 53-60 Recovering High-Level Structure of Software Systems Using a Minimum Description Length Principle....Pages 61-69 A System for Multi-agent Information Retrieval....Pages 70-77 All There Is to the Mind Is to Have the Right Genes, or, Consciousness as a Form of Genetic Engineering....Pages 78-86 Towards Robust Collaborative Filtering....Pages 87-94 GVR: A New Genetic Representation for the Vehicle Routing Problem....Pages 95-102 An Empirical Comparison of Particle Swarm and Predator Prey Optimisation....Pages 103-110 Data Mining Support for Case-Based Collaborative Recommendation....Pages 111-118 The Feasibility of Machine Learning for Query Answering — An Experiment in Two Domains....Pages 119-126 Meta-knowledge Annotation for Efficient Natural-Language Question-Answering....Pages 127-134 Financial Time Series Modelling Using Neural Networks: An Assessment of the Utility of a Stacking Methodology....Pages 137-143 Experiments in Sparsity Reduction: Using Clustering in Collaborative Recommenders....Pages 144-149 Identification of Visual Features Using a Neural Version of Exploratory Projection Pursuit....Pages 150-157 How People Compare an Item’s Placement in Two Alternative Categories....Pages 158-164 Investigations into Market Index Trading Models Using Evolutionary Automatic Programming....Pages 165-170 An Interactive Story Engine....Pages 171-176 Coherence, Explanation, and Bayesian Networks....Pages 177-182 Combining Case-Based Reasoning and Analogical Reasoning in Software Design....Pages 183-189 Combination Methods for Improving the Reliability of Machine Translation Based Cross-Language Information Retrieval....Pages 190-196 A System for Music Information Retrieval....Pages 197-202 A New Bayesian Network Structure for Classification Tasks....Pages 203-208 Evaluating Preference-Based Feedback in Recommender Systems....Pages 209-214 Design of a Musical Instrument Classifier System Based on Mel Scaled Cepstral Coefficient Supervectors and a Supervised Two-Layer Feedforward Neural Network....Pages 215-220 An Interactive Learning Environment for Knowledge Engineering....Pages 221-227 Customising a Copying-Identi.er for Biomedical Science Student Reports: Comparing Simple and Smart Analyses....Pages 228-233 A Hybridised GA for the Steiner Minimal Tree Problem....Pages 234-239 Speaking Autonomous Intelligent Devices....Pages 240-245 The Arti?cial Intelligence And Cognitive Science Conference Has Taken Place Annually Since 1988. It Provides A Forum For The Exchange Of Ideas And The P- Sentation Of Results Relating To Work Conducted Both In Ireland And Worldwide. The Conference Spans A Large Number Of ?elds Including Case-based Reas- Ing, Cognitive Modeling, Constraint Processing, Data Mining, Evolutionary C- Putation, Intelligent Agents, Intelligent Information Retrieval, Knowledge Rep- Sentation And Reasoning, Learning, Natural Language Processing, Neural Networks, Perception And Planning, Robotics, And Scheduling. Aics 2002 Was The Thirteenth Conference In The Series And Took Place At U- Versityoflimerickon12–13september.inadditiontothe16regularpapersand 17 Concise Papers Accepted For Presentation, We Were Delighted To Welcome Two Prestigious Keynote Speakers Both ?tting In With The Conference Theme ‘towards Bio-inspired Computing’. They Were David Goldberg Of University Of Illinois At Urbana-champaign, And Dario Floreano Of The Swiss Federal Institute Of Te- Nology. I Would Like To Take This Opportunity To Thank Our Sponsors Qad Ireland And University Of Limerick, As Well As All Those Who Were Involved In The Organisation Of The Conference Including The Co-chairs, Programme Committee Members, And Conference Administrators. June 2002 Richard F. E. Sutcli?e Organisation Aics 2002 Was Organized By The Department Of Computer Science And Inf- Mation Systems, University Of Limerick, In Association With The Arti?cial Int- Ligence Association Of Ireland. On The Usefulness Of Extracting Syntactic Dependencies For Text Indexing / Miguel A. Alonso, Jesus Vilares And Victor M. Darriba -- Using Latent Semantic Indexing As A Measure Of Conceptual Association For Noun Compound Disambiguation / Alan M. Buckeridge And Richard F.e. Sutcliffe -- Radar: Finding Analogies Using Attributes Of Structure / Brian P. Crean And Diarmund O'donoghue -- Classifying Languages Based On Speech Rhythm / Fred Cummins -- Finding Agents In A Two-dimensional Boolean Stam / Jim Doran -- Neuro-symbolic System For Forecasting Red Tides / Florentino Fdez-riverola, Juan M. Corchado And Jesus M. Torres -- Improved Learning For Hidden Markov Models Using Penalized Training / Bill Keller And Rudi Lutz. Michael O'neill ... [et Al.] (eds.). Includes Bibliographical References And Index. For Information Retrieval (IR) tasks, documents are frequently represented through a set of index terms or representative keywords.