Adrian-Gabriel CHIFU

Ph.D., Associate Professor
FEG - Aix-Marseille Université

See my publications


Here you can find a list of my publications. Please feel free to check out their .pdf versions.

International journal papers

  • Julie Ayter, Adrian Chifu, Sebastien Déjean, Cecile Desclaux, Josiane Mothe.
    Statistical Analysis to Establish the Importance of Information Retrieval Parameters.
    In: Journal of Universal Computer Science, Consortium J.UCS, Special Issue Information Retrieval and Recommendation, Vol. 21 N. 13 (2015), p. 1767-1789, December 2015.
  • Adrian Chifu, Florentina Hristea, Josiane Mothe, Marius Popescu.
    Word Sense Discrimination in Information Retrieval: A Spectral Clustering-based Approach.
    In: Information Processing & Management, Elsevier, Vol. 51, p. 16-31, March 2015.
  • Adrian Chifu, Radu Tudor Ionescu. Word Sense Disambiguation to Improve Precision for Ambiguous Queries.
    In: Central European Journal of Computer Science, Versita, co-éditeur Springer Verlag, Londres - GB, Vol. 2 N. 4, p. 398-411, December 2012.

International conference papers

  • NEW! Adrian-Gabriel Chifu, Sébastien Déjean, Stefano Mizzaro, Josiane Mothe.
    Human-Based Query Difficulty Prediction
    In: 39th European Conference on Information Retrieval, ECIR 17, April 2017.
    (to appear)
  • Adrian Chifu, Sébastien Fournier.
    SegChainW2V: Towards a generic automatic video segmentation framework, based on lexical chains of audio transcriptions and word embeddings.
    In: 20th International Conference on Knowledge Based and Intelligent Information and Engineering Systems, KES2016, September 2016.
  • Adrian Chifu, Sébastien Fournier.
    SegChain: Towards a generic automatic video segmentation framework, based on lexical chains of audio transcriptions.
    In: 6th International Conference on Web Intelligence, Mining and Semantics (WIMS'2016), 2016.
    Access ACM:
  • Radu Tudor Ionescu, Adrian Chifu, Josiane Mothe.
    DeShaTo: Describing the Shape of Cumulative Topic Distributions to Rank Retrieval Systems without Relevance Judgments (short paper).
    In: Symposium on String Processing and Information Retrieval (SPIRE 2015), London, UK, 01/09/2015-04/09/2015, Springer, p. 75-87, September 2015.

National conference papers

  • Adrian Chifu, Serge Molina, Josiane Mothe.
    MyBestQuery: A serious game to collect manual query reformulation (regular paper).
    In: Colloque Veille Stratégique Scientifique et Technologique (VSST 2016), Rabat (Morocco), 18/10/2016-20/10/2016, 2016.
  • Adrian Chifu, Serge Molina, Josiane Mothe.
    MyBestQuery: un jeu sérieux pour apprendre des utilisateurs (poster).
    In: Conférence francophone en Recherche d'Information et Applications (CORIA 2016), Toulouse, 08/03/2016-11/03/2016, Association Francophone de Recherche d'Information et Applications (ARIA), March 2016.
  • Adrian Chifu, Léa Laporte, Josiane Mothe.
    La prédiction efficace de la difficulté des requêtes : une tâche impossible? (regular paper) (short presentation).
    In: Conférence francophone en Recherche d'Information et Applications (CORIA 2015), Paris, 18/03/2015-20/03/2015, Association Francophone de Recherche d'Information et Applications (ARIA), p. 189-204, March 2015.
  • Julie Ayter, Cecile Desclaux, Adrian Chifu, Josiane Mothe, Sébastien Déjean.
    Performance Analysis of Information Retrieval Systems (regular paper).
    In: Spanish Conference on Information Retrieval, Coruna, 19/06/2014-20/06/2014, Springer-Verlag, (electronic support), June 2014.
  • Adrian Chifu, Josiane Mothe.
    Expansion sélective de requêtes par apprentissage (regular paper).
    In: Conférence francophone en Recherche d'Information et Applications (CORIA 2014), Nancy, France, 19/03/2014-21/03/2014, LORIA, p. 231-246, March 2014.
  • Adrian Chifu.
    Prédire la difficulté des requêtes : la combinaison de mesures statistiques et sémantiques (short paper).
    In: Conférence francophone en Recherche d'Information et Applications (CORIA 2013), Neuchatel, Suisse, 03/04/2013-05/04/2013, Université de Neuchétel, p. 191-200, April 2013.

Position papers

  • NEW! Magalie Ochs, Adrian Chifu, Sebastien Fournier, Evelyne Lombardo, Ivan Madjarov, Patrice Bellot.
    Vers une personnalisation des environnements d’apprentissages à l’expérience émotionnelle de l’apprenant.
    In: ORPHEE RDV 2017, Font Romeu (France), 30/01/2017-02/02/2017, 2017.

Other publications

  • Adrian Chifu.
    Presentation, Thesis research & SegChainW2V: Towards a Generic Automatic Video Segmentation Framework, based on Lexical Chains of Audio Transcriptions and Word Embeddings.
    Seminary (Séminaire d'accueil des enseignants-chercheurs de la FEG). December 2016.
  • Adrian Chifu.
    Expansion sélective de requêtes par apprentissage.
    Seminary. February 2014.
  • Adrian Chifu.
    Difficult query predictors: combining statistical and semantic measures.
    Seminary. February 2013.


Here you can find a few details regarding my Ph.D. thesis. Please feel free to check out the manuscript.


  • Title: Adapting information retrieval systems to contexts: the case of query difficulty
  • University: Université de Toulouse Paul Sabatier
  • Research Lab: Institut de Recherche en Informatique de Toulouse (IRIT)
  • Advisor: Prof. Josiane MOTHE
  • Defense date: June 15th, 2015
  • Keywords: Information retrieval, Machine learning, Difficult queries, Selective information retrieval, Query expansion, Disambiguation, Classification.


In the search engine environment, users submit queries according to their information need. In response to a query, the system retrieves and displays a list of documents which it considers of interest for the user. The user checks the results and decides what information is actually relevant to his information need. However, retrieved documents for some queries may not be satisfactory for the user. The queries for which the search engine cannot retrieve relevant information are called difficult. The query difficulty represents the research context of this thesis. We specifically aim at adapting the information retrieval systems with respect to difficult queries, in order to improve the retrieval quality.

Term ambiguity may be the cause of difficulty. For example, the query "orange" is ambiguous, since the engine does not know whether it refers to the fruit, to color, or to the telephone company. We have developed a method for disambiguation of queries in order to get better search results. This method works best on difficult query, result that motivates our research in predicting the difficulty. We also provide combinations of the difficulty predictors to improve the prediction quality of individual predictors. The search results can also be improved by expanding queries, process that adds terms to the initial query. We propose an automatic method of learning to classify queries according to query expansion variants. Finally, we try to optimize a parameter to improve a query expansion model.



Here is some of my teaching material (French and English). Please feel free to explore.

NEW! Managing databases: SQL and NoSQL (EN)



NEW! Analyse et fouille de données (FR)




Techniques d'accès à l'information (FR)



Analyses exploratoires multidimensionnelles et visualisations (FR)


Big Data: Introduction to python (EN)



Practice More

NoSQL - mongoDB (FR)




Programmation sous R (Marketing quantitatif) (FR/EN)




Contact me

If you are an academic willing to do research with me, or you represent an enterprise with some interesting proposal, or you are a student having some questions for which I might have an answer , or... you are anyone that would like to reach me, please fill in this form and I will get back to you as soon as possible. Thank you!