no code implementations • LREC 2022 • Edmond Menya, Mathieu Roche, Roberto Interdonato, Dickson Owuor
We find these thematic features rich enough to improve epidemiological document classification over a smaller data set than initially used in PADI-Web classifier.
no code implementations • EMNLP (Louhi) 2020 • Sarah Valentin, Mathieu Roche, Renaud Lancelot
Animal diseases-related news articles are richin information useful for risk assessment.
no code implementations • 26 Apr 2024 • Rémy Decoupes, Roberto Interdonato, Mathieu Roche, Maguelonne Teisseire, Sarah Valentin
This study introduces four indicators to assess these distortions, by comparing geographical and semantic distances.
1 code implementation • 30 Mar 2023 • Nejat Arinik, Roberto Interdonato, Mathieu Roche, Maguelonne Teisseire
In the context of Epidemic Intelligence, many Event-Based Surveillance (EBS) systems have been proposed in the literature to promote the early identification and characterization of potential health threats from online sources of any nature.
no code implementations • 15 Jan 2021 • Sarah Valentin, Elena Arsevska, Aline Vilain, Valérie De Waele, Renaud Lancelot, Mathieu Roche
This paper describes a method for annotation of epidemiological information in animal disease-related news articles.
no code implementations • LREC 2020 • Sarah Valentin, Renaud Lancelot, Mathieu Roche
We detail the processing of multilingual online sources by PADI-web and analyse the translated outputs in a case study
no code implementations • 16 Apr 2019 • Mathieu Roche
This position paper presents a comparative study of co-occurrences.
no code implementations • LREC 2018 • Eric Kergosien, Amin Farvardin, Maguelonne Teisseire, Marie-No{\"e}lle Bessagnet, Joachim Sch{\"o}pfel, St{\'e}phane Chaudiron, Bernard Jacquemin, Annig Lacayrelle, Mathieu Roche, Christian Sallaberry, Jean Philippe Tonneau
no code implementations • JEPTALNRECITAL 2016 • Sarah Zenasni, Maguelonne Teisseire, Mathieu Roche, Eric Kergosien
Dans un second temps, nous identifions de nouvelles relations spatiales qui pr{\'e}c{\`e}dent les entit{\'e}s spatiales (par exemple, sur, par, pres, etc.).
no code implementations • LREC 2016 • Wejdene Khiari, Mathieu Roche, Asma Bouhafs Hafsia
The experiments were conducted on two corpora: an elongated SMS corpus (i. e. repetitions of characters in messages) and a non-elongated SMS corpus.
no code implementations • LREC 2016 • Juan Antonio Lossio-Ventura, Clement Jonquet, Mathieu Roche, Maguelonne Teisseire
Polysemy detection is a first step for Word Sense Induction (WSI), which allows to find different meanings for a term.
no code implementations • LREC 2016 • Elena Arsevska, Mathieu Roche, Sylvain Falala, Renaud Lancelot, David Chavernac, Pascal Hendrikx, Barbara Dufour
Our method combines a text mining approach to extract terms from corpora of relevant disease outbreak documents, and domain expert elicitation (Delphi method) to propose expressions and to select relevant combinations between terms obtained with text mining.
no code implementations • JEPTALNRECITAL 2015 • Soumia Lilia Berrahou, Patrice Buche, Juliette Dibie-Barth{\'e}lemy, Mathieu Roche
La deuxi{\`e}me {\'e}tape du processus, une fois l{'}espace de recherche r{\'e}duit aux variants d{'}unit{\'e}s, utilise une nouvelle mesure de similarit{\'e} permettant d{'}identifier automatiquement les variants d{\'e}couverts par rapport {\`a} un terme d{'}unit{\'e} d{\'e}j{\`a} r{\'e}f{\'e}renc{\'e} dans la RTO avec un taux de pr{\'e}cision de 82{\%} pour un seuil au dessus de 0. 6 sur le corpus {\'e}tudi{\'e}.
no code implementations • LREC 2014 • C{\'e}dric Lopez, Best, Reda ji, Mathieu Roche, Rachel Panckhurst
In this paper, we propose a method for aligning text messages (entitled AlignSMS) in order to automatically build an SMS dictionary.