Master in Informatics and Computing Engineering
Information Description, Storage and Retrieval
Instance: 2020/2021
—

By the end of this class, the student should be able to:

• describe a test collection: documents, topics, relevance judgements;
• explain the need for specific evaluation methods in information retrieval;
• define precision, recall and their variants;
• interpret a precision vs recall graph;

1. Evaluation in Information Retrieval
   • Test collections
   • IR measures: precision, recall, P@n, F, MAP
   • Evaluation of ranked results

• Evaluation in Information Retrieval

• W. Bruce Croft, Donald Metzler, Trevor Strohman, Search Engines: Information Retrieval in Practice, Slides for chapters 2, 7, 8, accessed October 2019
• Ricardo Baeza-Yates, Berthier Ribeiro-Neto, Modern Information Retrieval: The Concepts and Technology behind Search, Slides for Chapter 3: Modeling, Chapter 4: Retrieval Evaluation, accessed October 2020
• Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval, Chapter 6, 7, 8, 11, 12, accessed October 2020
• Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval, Slides for chapters 6, 7, 8, 11, 12, accessed October 2020

• Experiment with full-text indexing tools.
• Milestone #2: define information needs for the full-text search task.
• Milestone #2: perform indexing experiments in the project collection.

• Evaluation in Information Retrieval. Test collections. IR measures: precision, recall, P@n, F, MAP.
• Evaluation of non-ranked results. Evaluation of ranked results. Relevance judgements.
• Work on Milestone 2 in the course project (Information Retrieval).
• Indexing experiments on the working collection.
• Definition of retrieval features for the domain.

— MCR, JCL, SSN

« Previous | Index | Next »