====== GINF533U - Information Access and Retrieval ======

Available from Master 2 [[http://mosig.imag.fr/ProgramEn/M2S1|MOSIG]]
and [[https://iam.imag.fr/m2tracks#data_science_ds|MSIAM]].  [[http://ufrima.imag.fr/ue/WebFormation/ue.php?code=GINF533U&ismat=&lang=en|Course Description]]

This course is given by [[http://mrim.imag.fr/User/jean-pierre.chevallet/|Jean-Pierre Chevallet]], [[http://lig-membres.imag.fr/mulhem/|Philippe Mulhem]] and [[http://lig-membres.imag.fr/quenot/|Georges Quénot]] from the [[http://lig-mrim.imag.fr/|Multimedia Information Modeling and Retrieval]] (MRIM) research group of the [[https://www.liglab.fr/en|Grenoble Informatics Laboratory]] (LIG).

Contact: [[mailto:Georges.Quenot@imag.fr"|Georges.Quenot@imag.fr]]

Part I. Foundations of Information Retrieval (Philippe Mulhem, Jean-Pierre Chevallet)
  * Course 1: {{:m2r_mosig_iar_2016_chapter_01_information_retrieval_basics.pdf|Information retrieval basics}} (P. Mulhem).
  * Course 2: {{:M2R MOSIG IAR Natural language processing for information retrieval.pdf|Natural language processing for information retrieval}} (J.-P. Chevallet).
  * Course 3: {{:m2r_mosig_iar_chapter_02_classical_models_for_information_retrieval.pdf|Classical models for information retrieval}} (P. Mulhem).
  * Course 4: {{:probabilistic_information_retrieval.pdf|Probabilistic IR Models}}. Details on Dirichlet Smoothing language models implementation using inverted files {{::dir-details.pdf|here}} (P. Mulhem).


Part II: Web and social networks (Philippe Mulhem)
  * Course 5: {{:web_ir.pdf|Web information retrieval}}.
  * Course 6: coming soon.
  * Course 7-8: coming soon.


Part III: Multimedia indexing and retrieval (Georges Quénot)
  * Course 9: {{:m2-mosig-iar-9.pdf|Visual content representation and retrieval}}.
  * Course 10: {{:m2-mosig-iar-10.pdf|Classical machine Learning for multimedia indexing}}.
  * Course 11-12: {{:m2-mosig-iar-11-12.pdf|Deep learning for multimedia indexing and retrieval}}.


The examination will be on January 22, 2018 from 2 to 4pm in ENSIMAG Amphi E. Course materials, the three papers related to the examinations, personal notes, and calculators (without network capabilities) are allowed. 
You will have to answer questions on two main topics that occur in the lessons. You are expected to do a research work on the papers, in a way to understand them and to be able to comment then.
The first topic is related to classical term weightings and the papers to read are:
  * [1] Fanghong Jian, Jimmy Xiangji Huang, Jiashu Zhao, Tingting He, and Po Hu. 2016. A Simple Enhancement for Ad-hoc Information Retrieval via Topic Modelling. ACM SIGIR '16. ACM, New York, NY, USA, 733-736. {{:p733-jian.pdf|pdf}}. __Do not focus on part 5.3., as it describes others approaches irrelevant for the exam.__
  * [2] Jiaul H. Paik. 2013. A novel TF-IDF weighting scheme for effective ranking. In Proceedings of the 36th international ACM SIGIR '13. ACM, New York, NY, USA, 343-352. Link to the pdf document : [[http://www.tyr.unlu.edu.ar/tallerIR/2014/papers/novel-tfidf.pdf]]. __Focus on the section 3 only, as it is the relevant part related to understand the paper [1].__
  * Details about the test collections used in the paper [1] are in [[http://ciir.cs.umass.edu/pubfiles/ir-464.pdf]] (subsection 4.1) and [[https://pdfs.semanticscholar.org/148c/88ef5f96faa76f77b0317a2d8c683a067bdd.pdf]] (subsection 5.1).

The second topic is related to neural networks with "shortcut connections" for image classification. The paper to read is:
  * [3] Huang, Gao and Liu, Zhuang and van der Maaten, Laurens and Weinberger, Kilian Q., Densely connected convolutional networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [[http://openaccess.thecvf.com/content_cvpr_2017/papers/Huang_Densely_Connected_Convolutional_CVPR_2017_paper.pdf]].

**Be sure to bring with you a copy of the three research papers as they will NOT be redistributed with the examination subject.** These can be annotated by you.




Reference to IR books or papers
  * [[http://nlp.stanford.edu/IR-book/|Introduction to Information Retrieval, http://nlp.stanford.edu/IR-book/]]
  * [[https://ciir.cs.umass.edu/irbook/|Search Engines Information Retrieval in Practice, https://ciir.cs.umass.edu/irbook/]]