声明
摘要
Abstract
CONTENTS
Symbols and Abbreviations
Chapter 1 Introduction
1.1 Supervised Learning
1.2 Ranking for Information Retrieval
1.3 Focus and Contributions
1.4 Outline of This Thesis
Chapter 2 Background and Related Work
2.1 Learning to Rank
2.1.1 Pointwise Learning to Rank Approach
2.1.2 Pairwise Learning to Rank Approach
2.1.3 Listwise Learning to Rank Approach
2.2 Evaluation Measures
2.2.1 Mean Average Precision
2.2.2 Normalized Discounted Cumulative Gain
2.3 Data Envelopment Analysis
2.3.1 Ranking of DMUs
Chapter 3 DEA-based Listwise Rank Learning Method
3.1 Modified DEA Models
3.2 DEARank Algorithm
3.3 Theoretical Analysis
Chapter 4 Experimental Evaluations
4.1 Experimental Setting
4.2 Experimental Results
4.3 Experiments with a Reduced Pool
Chapter 5 Discussions and Conclusions
5.1 Error Diversity and Local Fitting
5.2 Feature Subset Weighting Strategy
5.3 Conclusions
Acknowledgments
Reference
List of Publications