GBX9MO23 - Information Access and Retrieval - 2018-2019

Available from Master 2 MOSIG and MSIAM. Course Description

This course is given by Jean-Pierre Chevallet, Philippe Mulhem, Lorraine Goeuriot and Georges Quénot from the Multimedia Information Modeling and Retrieval (MRIM) research group of the Grenoble Informatics Laboratory (LIG).

Contact: Georges.Quenot@imag.fr

Part I. Foundations of Information Retrieval (Jean-Pierre Chevallet)

• Course 1: Information retrieval basics (J.-P. Chevallet).
• Course 2: Classical models for information retrieval (J.-P. Chevallet).
• Course 3: Probabilistic IR Models. (J.-P. Chevallet).
• Course 4: Natural language processing for information retrieval (J.-P. Chevallet).

Part II: Web, social networks and health (Philippe Mulhem, Lorraine Goeuriot)

• Course 5: Web information retrieval (P. Mulhem).
• Course 6: IR evaluation (L. Goeuriot / P. Mulhem).
• Course 7: Personalization and social information retrieval (P. Mulhem).
• Course 7: Medical information retrieval (L. Goeuriot).

Part III: Multimedia indexing and retrieval (Georges Quénot)

• Course 9: Visual content representation and retrieval (G. Quénot).
• Course 10: Classical machine Learning for multimedia indexing (G. Quénot).
• Course 11-12: Deep learning for multimedia indexing and retrieval updated January 6, 2019 (G. Quénot).

Reference to IR books or papers

• Introduction to Information Retrieval, http://nlp.stanford.edu/IR-book/
• Search Engines Information Retrieval in Practice, https://ciir.cs.umass.edu/irbook/

The examination will be on January 28, 2019 from 1 to 3pm in ENSIMAG C005. Warning: the time has been advanced and the room has changed (see ADE). Course materials, the two papers related to the examinations, personal notes, and calculators (without network capabilities) are allowed. You will have to answer questions on topics that occur in the lessons. You are expected to do a research work on the two papers proposed below, in a way to understand them and to be able to comment then. You must also take time to read complementary informations in order to understand the papers. The first topic is related to IR text data structure and models. The second one is related to building good representation for content-based image retrieval. Be sure to bring with you a copy of the two research papers as they will NOT be redistributed with the examination subject. These can be annotated by you. The bibliography and appendices are part of the papers.

The papers to read are:

• “BitFunnel: Revisiting Signatures for Search” https://danluu.com/bitfunnel-sigir.pdf or https://dl.acm.org/citation.cfm?doid=3077136.3080789 from Bob Goodwin, Michael Hopcroft, Dan Luu, Alex Clemmer, Mihaela Curmei, Sameh Elnikety and Yuxiong He, in the Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.
• “Deep Image Retrieval: Learning global representations for image search” https://arxiv.org/pdf/1604.01325 from Albert Gordo, Jon Almazan, Jerome Revaud, Diane Larlus, ECCV 2016.

Note: for the second paper, the part on automatic data cleaning is not concerned, there will not be questions on this.

Last year examination: gbx9mo23-2017-2018-exam.pdf

The second session examination will take place on April 16, from 9am to 11am in rooms D208 and D211 (ENSIMAG building).
It will be an oral examination of 30 minutes in total, 15 minutes with Georges Quénot (D208) and 15 minutes with Jean-Pierre Chevallet (D211).
There is no new papers to study for this sessions. There will be short exercises and questions on the course and maybe some on the papers studied for session 1 examination.