[Defended thesis] Jacques Fize: Matching between massive and heterogeneous data : application to biodiversity data

Matching between massive and heterogeneous data : application to biodiversity data

• Starting date: October 2016
• University: University of Montpellier
• PhD school: I2S – Information, Structures, Systèmes
• Scientific field: IT, data sciences
• Thesis management: Mathieu Roche, Cirad Tetis et Maguelonne Teisseire, Irstea Tetis
• Funding: Cirad – Irstea
• #DigitAg: Labeled PhD – Axes 5  et 4 – Challenges : sujet transverse, 8

Keywords: Text mining, automatic language processing, thematic similarity, spatial similarity, temporal similarity, heterogeneous data, biodiversity data

Abstract: In scientific literature, few approaches exists for matching heterogeneous data in a generic way. As part of this thesis, propositions will be established in multidisciplinary ways of matching under 3 axes : thematic matching, spatial matching and temporal matching. The identification of pertinent descriptors will be established under these 3 axes using symbolic, statistic and semantic methods and the use of NLP methods for exploring textual data.

Contact :  mathieu.roche [AT] cirad.fr

Social networks:  site – GitHub – ResearchGate – LinkedIn

Communications & Papers

Download the thesis manuscript: « Mise en correspondance de données textuelles hétérogènes fondée sur la dimension spatiale »

• Fize J., Roche M., Teisseire M. (2018) Gemedoc: A Text Similarity Annotation Platform. In: Silberztein M., Atigui F., Kornyshova E., Métais E., Meziane F. (eds) Natural Language Processing and Information Systems. NLDB 2018. Lecture Notes in Computer Science, vol 10859. Springer, Cham – https://doi.org/10.1007/978-3-319-91947-8_3
• Fize J., Roche M., Teisseire M. (2018). Matching heterogeneous textual data using spatial features 13th International Workshop on Spatial and Spatiotemporal Data Mining (SSTDM-18) (to appear)