GBX9MO23 - Information Access and Retrieval

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

Contents / schedule (might be updated):

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 (NB: not presented this year) (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 8: Medical information retrieval (L. Goeuriot).

Part III: Multimedia indexing and retrieval (Georges Quénot)

• Mathematics Reminders: Linear algebra and convolutions (differential calculus and “conv. layers” in course 11-12) (G. Quénot).
• Course 9: Visual content representation and retrieval (only introduction and color / texture / points of interest descriptors) (G. Quénot).
• Course 10: Classical machine Learning for multimedia indexing (part on LSH is excluded) (G. Quénot).
• Course 11-12: Deep learning for multimedia indexing and retrieval (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/

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. 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, if any, are part of the papers.

Jianfeng Dong, Xirong Li, Chaoxi Xu, Shouling Ji, Yuan He, Gang Yang, Xun Wang,
Dual Encoding for Zero-Example Video Retrieval,
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9346-9355.
http://openaccess.thecvf.com/content_CVPR_2019/papers/Dong_Dual_Encoding_for_Zero-Example_Video_Retrieval_CVPR_2019_paper.pdf

Hamed Zamani, Mostafa Dehghani, W. Bruce Croft, Erik Learned-Miller, and Jaap Kamps. 2018. From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing.
In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM '18). ACM, New York, NY, USA, 497-506.
https://ciir-publications.cs.umass.edu/pub/web/getpdf.php?id=1302
Important Notice: For the second paper, you are expected to gather information about word embeddings on your own, in a way to understand the paper and to answer to the questions that will be asked.

2017-2018 examination: gbx9mo23-2017-2018-exam.pdf, papers:
https://www.researchgate.net/publication/305081616_A_Simple_Enhancement_for_Ad-hoc_Information_Retrieval_via_Topic_Modelling,
http://www.tyr.unlu.edu.ar/tallerIR/2014/papers/novel-tfidf.pdf,
http://openaccess.thecvf.com/content_cvpr_2017/papers/Huang_Densely_Connected_Convolutional_CVPR_2017_paper.pdf

2018-2019 examination: gbx9mo23-2018-2019-exam.pdf, papers:
https://danluu.com/bitfunnel-sigir.pdf,
https://arxiv.org/pdf/1604.01325.

No information yet.

• Integrating reasoning in deep learning explanations (Georges Quénot and Marie-Christine Rousset)
• Interactive Information Retrieval Systems Evaluation though Synthetic Users (Philippe Mulhem and Francis Jambon)
• Justification of Deep Video Retrieval Results (Georges Quénot and Philippe Mulhem)
• Multidimensional representation of medical heterogeneous data using neural networks (Lorraine Goeuriot and Didier Schwab)
• Neural Deep Transformers and Sparse Representations for Inverted Indexing (Jean-Pierre Chevallet and Didier Schwab)
• Prediction of patient's re-access to the healthcare system (Lorraine Goeuriot and Didier Schwab)
• Quantitative Data Analysis for Information Retrieval Evaluation (Lorraine Goeuriot and Philippe Mulhem)
• Toward explainable embeddings-based and Pseudo relevance Feedback query expansions in Information Retrieval (Philippe Mulhem, Jean-Pierre Chevallet and Catherine Berrut)
• Web search engine biases(Philippe Mulhem, Lydie Du-Bousquet and Lorraine Goeuriot)