Tracking highly qualified diasporas with semantic mining of web search results

We are currently using reinforcement learning on biographical web search results to track professional mobility of highly qualified migrations. We suppose that mining the web with semantic methods could provide valuable data for migration sociologist, and furthermore it could allow the development of a new generation of expert mining systems.

Funding: Ecos Nord (2016-2020)
Budget: ~64k€
Consortium: LIPN, Télécom-Paristech, IRD, IIMAS/UNAM, CRIM/UNAM (Mexico)


Robot experience stories generation

When humans get back home, there is usually another human there to ask: “How was your day?” Our work aims at providing robots with the natural language capabilities to answer a similar question, not exactly about their day, but about their experience performing a certain task. Robxp stories are narratives composed of the robot's holistic perception of a recently performed task: navigation, visual perceptions and action descriptions.

Funding: AUF-PIRAT (2015-2016)
Budget: 11k€
Consortium: LIPN, LORIA, IIMAS/UNAM (Mexico)


Robot Experience Stories: first person generation of robotic task narratives in SitLog

Garcia Flores, J., Meza, I., Colin, E., Gardent, C., Gangemi, A. and Pineda, L. (2018, forthcoming)Journal of Intelligent and Fuzzy Systems.

Cross-domain deception detection using support vector networks

Hernandez-Castañeda, A, Calvo, H., Gelbukh A. and Garcia Flores, J.J. (2017, February) Soft Computing, 21(3), 585-595. doi:10.1007/s00500-016-2409-2

Blog annotation: from corpus analysis to automatic tag suggestion

Garrido-Marquez, I. Garcia Flores, J., Lévy, F. and Nazarenko, A. (2016, April) Research in Computing Science (CICLING 2016): Advances in Opinion Mining, Social Network Analysis, and Authorship Attribution, 110, 95-106.

Lipn-core: Semantic text similarity using n-grams, wordnet, syntactic analysis, ESA and information retrieval based features

Buscaldi, D., Le Roux, J., Garcia Flores, J.J. and Popescu, A. (2013) Second Joint Conference on Lexical and Computational Semantics (SEMEVAL 2013).

Tracking Researcher Mobility on the Web Using Snippet Semantic Analysis

Garcia Flores, J.J., Zweigenbaum, P., Yue, Z. and Turner, W. (2012) Advances in Natural Language Processing (JapTAL, 2012). Lecture Notes in Computer Science, 7614, 180-191. doi:10.1007/978-3-642-33983-7_18



Name Description Role URL source URL prototype
UnoporunO Web mining of highly qualified migrations project manager, developer
unoporunoDQN Reinforcement learning for highly qualified migrations tracking co-project manager
cartographies sonores World languages audio map of some of the languages studied by Labex EFL researchers. project manager
BNI Visual navigation on selected philosopher's ideas co-project manager
CCTV Multilingual Wikipedia topic visualization app for a sampled min-hashing topic extraction method. project manager
Golfred Robot experience stories generation project manager, co-developer
SOPA-Semeval Linear regression involving a soup of features for calculating semantic similarity between a pair of sentences (SEMEVAL-STS 2013-2015 system). co-developer

Students & teaching

Université Paris 13, Institut Galilée
Master in Computer Science EID2

Project Management

Theoretical and practical course on project management for Master-1 students. After the theory, the students spent 6 months developing a software development project for "real" clients. For the 2016 edition, the "client" were at a research institute in Mexico. Two student teams (14 students) developed the project, having virtual meetings with the clients on a weekly basis. At the end of the project, two of the students travelled to Mexico to present their work.

Ivan Garrido-Marquez (Phd student, LIPN, UP13)

Ivan's PhD focuses on semantic annotation methods which take into account quality measures and the dynamic revision of annotations. Ivan developed an 11 million words corpus of French blogs on cooking, law and technology as a testbed for the quality, redundancy, balance and re-annotation methods he's developing. Ivan's main supervisor is Adeline Nazarenko, François Lévy and me being Ivan's PhD co-supervisors.

Josué Urbina and Carl Posthuma (Engineering College, IIMAS, UNAM)

I am Josué's and Carl's co-supervisor of their professional practices at UNAM Engineering College, their main supervisor being Iván Vladimir Meza (IIMAS-UNAM, Mexico). Josué and Carl are working on a Deep-Q neural network based method for extracting biographical data from web search queries for the CARTOGRAFíA project.