[ Home ] – [ Research ] – [ Teaching ] – [ Resources ] – [ Misc ]
Nicolas Hernandez
Nicolas Hernandez
Maître de conférences - Associate Professor
Atlanstic LINA TALN CNRS UMR 6241 – Université de Nantes (rattaché à l'IUT - Département Informatique)
Presentation : Associate Professor in Computer Sciences at the University of Nantes and member of the LINA laboratory (UMR 6241 CNRS), I am interested in issues to do with accessing the content of (textual) documents. This research is carried out prior to NLP applications (such as summarization, information retrieval) or Semantic Web processing. In particular, my research interests focus both on semantic and discourse analysis methods to provide description of content structures, and on techniques of knowledge acquisition from corpora to support the initial analyses. His approach combines statistical methods and linguistics. I am also interested in NLP frameworks in particular the one based on Apache UIMA .
Keywords : Accessing the content of ( textual ) documents ; discourse analysis and modelling ; knowledge acquisition from corpus ; hybrid approaches (statistical with linguistic knowledge) ; NLP applications (such as summarization , reader and writer assistant ).
2007-… Création d'une communauté francophone autour de l'architecture UIMA http://uima-fr.org
2010-2012 TTC ; European project
2010-2013 Depart; Regional Project
2008-2010 C-Mantic ; ANR “Masse de données et Connaissances” ; LINA, ERTIM, LIMSI, INSERM
2007-2009 MILES ; Regional Project “Pays de Loire” ; It aims at developing a software architecture to identify speakers in oral corpora by using a joint analysis of sound signal and of its written transcription. Several Computer Sciences Laboratories are involved in this project; among them the LINA (Nantes, France) and the LIUM (Le Mans, France)
2006 - 2008 PIITHIE (Plagiat et Impact de l'Information Textuelle recHerchée dans un contexte InterlinguE) ; ANR Technologies Logicielles ; LIA et LINA, Advestigo, Synequa, Sylabs ; Co-coordinateur pour le LINA
2005 - 2006 Geosem (Géographie et Sémantique) ; Programme “Société de l’Information” ; GREYC, ERSS, ESO, LIUPPA, LATTICE, IRIT et EPFL
2000 - 2004 REGAL (Résumé Guidé par les Attentes du Lecteur) ; Projet Cognitique ; CEA, le LATTICE (UMR du CNRS) et le LIMSI (UPR du CNRS)
First French-speaking meeting around the framework Apache UIMA - Nantes, France, 7-11 July 2009 - As part of the 10th edition of the Libre Software Meeting (LSM/RMLL) under the conferences topic “Libre resources and software for scientific research” - Organized by LINA CNRS UMR 6241 - University of Nantes. We would like to use this opportunity to organize a special meeting around Apache UIMA to encourage the development of a user and developer French-speaking community (http://www.uima-fr.org)
International Symposium : Discourse and Document 2006 held in Caen (France), on June 15-16 2006. Member of the Program Committee and the Organising Committee. The aim of ISDD'06 is to bring together researchers interested in what can be called the “document level” in discourse linguistics, natural language processing, or document engineering.
TALN - RECITAL 2005 at Dourdan, France, 6-10 June 2005
Co-President of the organization board of RECITAL and member of its program committee. RECITAL is the francophone
young researchers
conference in Natural Language Processing. These conferences are organized under the auspices of the ATALA.
Financement du salaire d'un ingénieur pour 3 mois (LINA UMR 6241, N. Hernandez). Montant 8 461 €
Recipient for the proposal “Building a French speaking community around UIMA, gathering research, education and industrial partners, mainly in Natural Language Processing and Speech Recognizing domains”. The award amount is $19,000 USD. Ce prix récompense les travaux menés par Nicolas Hernandez en collaboration avec Fabien Poulard, Stergos Afantenos et Matthieu Vernier au sein de l'équipe TALN du LINA. The main objective of our proposal is ... ; Call and previous recipient award
Développement et Intégration sous Apache UIMA de composants de traitement automatique des langues. Intégration sous UIMA de composants de traitement de la parole. Valorisation par la mise en place et la gestion d'un portail pour la distribution des composants et l'animation de la recherche francophone en TAL (Traitement Automatique des Langues) et en TP (Traitement de la Parole) autour d'UIMA. Poste budgétaire : salaire d'un ingénieur sur 9 mois ; 1 serveur d'application ; déplacements chez les partenaires ; participation à conférence internationale ; Montant total 39 137, 44 euros
Still ongoing
2010
2009
2008
Most recent publications
This page list a number of bits of software I've developed which hopefully other people will find useful.
Other contributions
Nicolas Hernandez, Description et Détection Automatique de Structures de Textes, Thèse de doctorat informatique, Soutenue le 14 décembre 2004 à l'université Paris-Sud XI au laboratoire LIMSI/CNRS
The manuscript , a quick overview (jury, mots clefs, résumé, bibliographie, publications), slides of my defence, the bibliography (tex)