Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment: First PASCAL Machine Learning Challenges Workshop, MLCW 2005, Southampton, UK, April 11-13, 2005, Revised Selected Papers

Joaquin Quiñonero-Candela (auth.), Joaquin Quiñonero-Candela, Ido Dagan, Bernardo Magnini, Florence d’Alché-Buc (eds.)3540334270, 9783540334279

This book constitutes the thoroughly refereed post-proceedings of the First PASCAL (pattern analysis, statistical modelling and computational learning) Machine Learning Challenges Workshop, MLCW 2005, held in Southampton, UK in April 2005.

The 25 revised full papers presented were carefully selected during two rounds of reviewing and improvement from about 50 submissions. The papers reflect the concepts of three challenges dealt with in the workshop: finding an assessment base on the uncertainty of predictions using classical statistics, Bayesian inference, and statistical learning theory; the second challenge was to recognize objects from a number of visual object classes in realistic scenes; the third challenge of recognizing textual entailment addresses semantic analysis of language to form a generic framework for applied semantic inference in text understanding.

---

Table of contents :
Front Matter….Pages –
Evaluating Predictive Uncertainty Challenge….Pages 1-27
Classification with Bayesian Neural Networks….Pages 28-32
A Pragmatic Bayesian Approach to Predictive Uncertainty….Pages 33-40
Many Are Better Than One: Improving Probabilistic Estimates from Decision Trees….Pages 41-55
Estimating Predictive Variances with Kernel Ridge Regression….Pages 56-77
Competitive Associative Nets and Cross-Validation for Estimating Predictive Uncertainty on Regression Problems….Pages 78-94
Lessons Learned in the Challenge: Making Predictions and Scoring Them….Pages 95-116
The 2005 PASCAL Visual Object Classes Challenge….Pages 117-176
The PASCAL Recognising Textual Entailment Challenge….Pages 177-190
Using Bleu-like Algorithms for the Automatic Recognition of Entailment….Pages 191-204
What Syntax Can Contribute in the Entailment Task….Pages 205-216
Combining Lexical Resources with Tree Edit Distance for Recognizing Textual Entailment….Pages 217-230
Textual Entailment Recognition Based on Dependency Analysis and WordNet ….Pages 231-239
Learning Textual Entailment on a Distance Feature Space….Pages 240-260
An Inference Model for Semantic Entailment in Natural Language….Pages 261-286
A Lexical Alignment Model for Probabilistic Textual Entailment….Pages 287-298
Textual Entailment Recognition Using Inversion Transduction Grammars….Pages 299-308
Evaluating Semantic Evaluations: How RTE Measures Up….Pages 309-331
Partial Predicate Argument Structure Matching for Entailment Determination….Pages 332-343
VENSES – A Linguistically-Based System for Semantic Evaluation….Pages 344-371
Textual Entailment Recognition Using a Linguistically–Motivated Decision Tree Classifier….Pages 372-384
Recognizing Textual Entailment Via Atomic Propositions….Pages 385-403
Recognising Textual Entailment with Robust Logical Inference….Pages 404-426
Applying COGEX to Recognize Textual Entailment….Pages 427-448
Recognizing Textual Entailment: Is Word Similarity Enough?….Pages 449-460
Back Matter….Pages –