book

Relevance Ranking for Vertical Search Engines

by Bo Long, Yi Chang

January 2014

Intermediate to advanced

264 pages

8h 49m

English

Morgan Kaufmann

Read now

Unlock full access

1.1 Defining the Area 1.2 The Content and Organization of This Book 1.3 The Audience for This Book 1.4 Further Reading

2.1 The Learning-to-Rank Approach 2.2 Joint Learning Approach from Clickthroughs 2.3 News Clustering 2.4 Summary
Introduction 3.1 Search Engines for Electronic Health Records 3.2 Search Behavior Analysis 3.3 Relevance Ranking 3.4 Collaborative Search 3.5 Conclusion
Introduction 4.1 Generic Visual Search System 4.2 Text-Based Search Ranking 4.3 Query Example-Based Search Ranking 4.4 Concept-Based Search Ranking 4.5 Visual Search Reranking 4.6 Learning and Search Ranking 4.7 Conclusions and Future Challenges
Introduction 5.1 Ranking Signals 5.2 Ranking Heuristics 5.3 Summary and Future Directions
6.1 An Overview of Entity Ranking 6.2 Background Knowledge 6.3 Feature Space Analysis 6.4 Machine-Learned Ranking for Entities 6.5 Experiments 6.6 Conclusions
Introduction 7.1 Related Work 7.2 Problem Formulation 7.3 Learning Aggregation Functions 7.4 Experiments 7.5 Conclusions and Future Work
Introduction 8.1 Sources of Evidence 8.2 Combination of Evidence 8.3 Evaluation 8.4 Special Topics 8.5 Conclusion
Introduction 9.1 The PCDF Model 9.2 Algorithm Derivation 9.3 Experimental Evaluation 9.4 Related Work 9.5 Conclusions

Content preview from Relevance Ranking for Vertical Search Engines

Entity Ranking

Abstract

Entity ranking is a recent paradigm that refers to retrieving and ranking related objects and entities from different structured sources in various scenarios. Entities typically have associated categories and relationships with other entities. In this chapter, we introduce how to build a Web-scale entity ranking system based on machine learned ranking models. Specifically, the entity ranking system usually takes advantage of structured knowledge bases, entity relationship graphs, and user data to derive useful features in order to facilitate semantic search with entities directly within the learning-to-rank framework. Similar to generic Web search ranking, entity pairwise preference can be leveraged to form the objective ...