Learning to Rank

By K. Horák et al
Read the original document by opening this link in a new tab.

Table of Contents

Introduction to Ranking
What is ranking?
Conventional Ranking Methods
Query - Dependent Models
Query - Independent Models
Learning to Rank
Training/Test Sets
Goal
True Story
Basic Approaches
Pointwise Approach
Pairwise Approach
Listwise Approach
Query - Dependent Ranking
Options
References

Summary

Learning to Rank provides an in-depth exploration of ranking algorithms and techniques. It covers various models such as TF-IDF, PageRank, and RankNet, explaining their applications in web search and information retrieval. The book discusses the challenges in optimizing evaluation measures and presents different approaches like Pointwise, Pairwise, and Listwise to address them. It also delves into query-dependent ranking strategies, offering insights on training models based on query similarities. With a focus on practical implementations and real-world examples, Learning to Rank is a valuable resource for researchers and practitioners in the field of information retrieval.
×
This is where the content will go.