Machine Learning Challenges

Evaluating Predictive Uncertainty, Visual Object Classification, and Recognizing Textual Entailment, First Pascal Machine Learning Challenges Workshop, MLCW 2005, Southampton, UK, April 11-13, 2005, Revised Selected Papers
2006
ISBN: 978-3-540-33427-9
Verlag: Springer Berlin Heidelberg

Buch, Englisch, Band 3944, 462 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 815 g

Reihe: Lecture Notes in Computer Science

This book constitutes the refereed post-proceedings of the First PASCAL Machine Learning Challenges Workshop, MLCW 2005. 25 papers address three challenges: finding an assessment base on the uncertainty of predictions using classical statistics, Bayesian inference, and statistical learning theory; second, recognizing objects from a number of visual object classes in realistic scenes; third, recognizing textual entailment addresses semantic analysis of language to form a generic framework for applied semantic inference in text understanding.

Zielgruppe

Research

Autoren/Hrsg.

Quinonero-Candela, Joaquin

D'Alché-Buc, Florence

Dagan, Ido

Magnini, Bernardo

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Logik, formale Sprachen, Automaten
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Wissensbasierte Systeme, Expertensysteme
• Mathematik | Informatik EDV | Informatik Programmierung | Softwareentwicklung Spiele-Programmierung, Rendering, Animation
• Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik Robotik
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Programmierung | Softwareentwicklung Grafikprogrammierung
• Mathematik | Informatik EDV | Informatik Programmierung | Softwareentwicklung Programmierung: Methoden und Allgemeines

Inhaltsverzeichnis

Evaluating Predictive Uncertainty Challenge.- Classification with Bayesian Neural Networks.- A Pragmatic Bayesian Approach to Predictive Uncertainty.- Many Are Better Than One: Improving Probabilistic Estimates from Decision Trees.- Estimating Predictive Variances with Kernel Ridge Regression.- Competitive Associative Nets and Cross-Validation for Estimating Predictive Uncertainty on Regression Problems.- Lessons Learned in the Challenge: Making Predictions and Scoring Them.- The 2005 PASCAL Visual Object Classes Challenge.- The PASCAL Recognising Textual Entailment Challenge.- Using Bleu-like Algorithms for the Automatic Recognition of Entailment.- What Syntax Can Contribute in the Entailment Task.- Combining Lexical Resources with Tree Edit Distance for Recognizing Textual Entailment.- Textual Entailment Recognition Based on Dependency Analysis and WordNet.- Learning Textual Entailment on a Distance Feature Space.- An Inference Model for Semantic Entailment in Natural Language.- A Lexical Alignment Model for Probabilistic Textual Entailment.- Textual Entailment Recognition Using Inversion Transduction Grammars.- Evaluating Semantic Evaluations: How RTE Measures Up.- Partial Predicate Argument Structure Matching for Entailment Determination.- VENSES – A Linguistically-Based System for Semantic Evaluation.- Textual Entailment Recognition Using a Linguistically–Motivated Decision Tree Classifier.- Recognizing Textual Entailment Via Atomic Propositions.- Recognising Textual Entailment with Robust Logical Inference.- Applying COGEX to Recognize Textual Entailment.- Recognizing Textual Entailment: Is Word Similarity Enough?.