Learning to Rank for Information Retrieval and Natural Language Processing

✍ Scribed by Hang Li

• Publisher: Morgan & Claypool Publishers
• Year: 2011
• Tongue: English
• Leaves: 115
• Series: Synthesis Lectures on Human Language Technologies #12
• Category: Library

✦ Table of Contents

Preface
Learning to Rank
Ranking
Learning to Rank
Ranking Creation
Ranking Aggregation
Learning for Ranking Creation
Learning for Ranking Aggregation
Learning for Ranking Creation
Document Retrieval as Example
Learning Task
Training and Testing
Training Data Creation
Feature Construction
Evaluation
Relations with Other Learning Tasks
Learning Approaches
Pointwise Approach
Pairwise Approach
Listwise Approach
Evaluation Results
Learning for Ranking Aggregation
Learning Task
Learning Methods
Methods of Learning to Rank
PRank
Model
Learning Algorithm
OC SVM
Model
Learning Algorithm
Ranking SVM
Linear Model as Ranking Function
Ranking SVM Model
Learning Algorithm
IR SVM
Modified Loss Function
Learning Algorithm
GBRank
Loss Function
Learning Algorithm
RankNet
Loss Function
Model
Learning Algorithm
Speed up of Training
LambdaRank
Loss Function
Learning Algorithm
ListNet and ListMLE
Plackett-Luce model
ListNet
ListMLE
AdaRank
Loss Function
Learning Algorithm
SVM MAP
Loss Function
Learning Algorithms
SoftRank
Soft NDCG
Approximation of Rank Distribution
Learning Algorithm
Borda Count
Markov Chain
Cranking
Model
Learning Algorithm
Prediction
Applications of Learning to Rank
Theory of Learning to Rank
Statistical Learning Formulation
Loss Functions
Relations between Loss Functions
Theoretical Analysis
Ongoing and Future Work
Bibliography
Author's Biography