Natalia Grabar

Affiliation: UMR 8163 Savoirs, Textes, Langage STL, U Lille natalia.grabar AT univ-lille.fr

CNRS Researcher (Chargée de Recherche classe normale CNRS) in Natural Language Processing (NLP), affiliated to the UMR 8163 STL, CNRS, U Lille.

I studied philology in Lviv University, Ukraine and then defended the PhD degree at the Université Paris 6, France in Medical Informatics.
My research is concerned with the Natural Language Processing applied to scientific and technical texts and to terminologies. The objective is to develop linguistic and statistical methods to access information and knowledge within documents. The results are exploited within contexts related to information retrieval, information extraction and text simplification.

Languages : Ukrainian (native), French and English; Russian (almost forgot); some notions in Spanish, Polish and Brazilian Portuguese; survival notions in some other languages.

Last news:

• October 16th, 2024 at PariSanté Campus, Paris, France: TIDS (Traitement Informatique des Données de Santé) workshop dedicated to clinical repositories.
  Registration
  
• October 8th, 2024 at PariSanté Campus, Paris, France
  Travaux en simplification de textes de santé
  Les Rencontres de l'ANS et de l'Inria : Meet-Up Natural Language Processing (NLP) Santé
  
• May 19th to 20th, 2024 in Blois, France: TIDS (Traitement Informatique des Données de Santé) workshop as part of the GdR MaDICS colloquium
  
• May 14th to 17th, 2023: ESIA summer school in IA and health
  
• May 12th, 2023: Resources for Ukrainian, as part of the ContribuLing 2023 event
  Registration (free)
  
• September, 2022: Ukraine joins Digital Europe programme (link)
  
• May 2022: Resources for Ukrainian, as part of the ContribuLing 2022 event
  
• March, 2022: Resources for Ukrainian
  
• February, 2022: Petition Stop war in Ukraine
  
• June, 2021: Conference RECITAL-TALN 2021 held online
  
• October, 2020: First call for papers for TALN 2021
  The event will be held in Lille, France or online according to the situation
  
• June 8th, 2020: DEFT NLP/IR challenge
  Tasks on clinical cases in French: semantic similarity, fine-grained information extraction
  Nancy, France
  Training data available on: https://deft.limsi.fr/2020/
  
• December 2nd, 2019:
  Atelier Interactions alimentation – médicaments : comment les maîtriser ?
  Eurasanté, Lille
  
• September 2019:
  Annuaire ATALA des entreprises travaillant en TAL
  Annuaire ATALA des équipes de TAL
  Annuaire ATALA des formations de TAL
  
• July 2019: TIA 2019
  Terminologie et intelligence artificielle, common workshop TALN/IC
  July 1st, Toulouse, France
  
• July 2019: DEFT NLP/IR challenge
  Tasks on clinical cases in French: indexing, semantic similarity, information extraction
  Workshop: July 2nd, Toulouse, France
  
• June 2019: Atelier de l'action ADOC (Entrepôts et analyse de documents) de MADICS dédié aux Données de l'Histoire de l'art et Archéologie, adossé à la conférence Inforsid 2019
  Atelier: 11 June 2019, Paris, France
  Jérôme Darmont, Natalia Grabar, Olivier Teste, Eds.
  
• May 17th, 2019, 2pm: Habilitation (HDR) defense
  Title: Adaptation de documents techniques pour les locuteurs non spécialisés
  Place: LIMSI, Orsay, bâtiment 507, RDC, salle de conférences
  Abstract: As any specialized area, the medical area handles very specific notions (like blepharospasm, alexitymia, appendicectomia), which are difficult to understand by non-specialized users. We propose a set of works which general objective is to adapt the content of technical health documents and to ensure their better understanding by non-specialists. To reach the objective, we propose a set of experiments, which are part of a complex and ambitious process:
  (1) categorization of documents according to their complexity;
  (2) detection of complex passages within documents;
  (3) acquisition of resources for the lexical and semantic simplification of documents;
  (4) alignment of parallel sentences from comparable corpora for detecting rules for syntactic transformation.
  Besides, a non-experimental part of the work is dedicated to the analysis of the existing work related to the evaluation of document simplification. Globally, the research work we are presenting is application research and motivated by real needs. Each step is performed with methods clearly described and tested, which results are evaluated, positioned within the existing work, and discussed. According to the steps and tasks, various methods are exploited (rule-based, machine learning, with and without the use of linguistic knowledge). At different steps of this work, il has also been necessary to build new resources (lexica, corpora...), which genesis is also described. In addition to the text simplification, the results and resources can be used for other Natural Language processing (NLP) applications and tasks (information retrieval and extraction, question-answering, textual entailment).
  Panel:
  • Pascale Sébillot, Professeur, INSA de Rennes, Rennes, France (rappoteur)
  • Cédrick Fairon, Professeur, Université Catholique de Louvain, Louvain-La-Neuve, Belgique (rapporteur)
  • Pierrette Bouillon, Professeur, Université de Genève, Genève, Suisse (rapporter)
  • Chantal Reynaud, Professeur, Université Paris-Sud, Orsay, France (examinateur)
  • Stefan Schulz, Professeur, Graz General Hospital and University Clinics, Graz, Autriche (examinateur)
  • Nabil Hathout, Directeur de Recherche CNRS, Toulouse, France (examinateur)
  • François Yvon, Professeur, Université Paris-Sud, CNRS, Orsay, France (garant)
• April 2019: SDRC-QDV project accepted within the MESHS Projet Emergent framework.
  Main investigators: Natalia Grabar, SDRC association
• March 2019: Call for papers. Atelier de l'action ADOC (Entrepôts et analyse de documents) de MADICS dédié aux Données de l'Histoire de l'art et Archéologie, adossé à la conférence Inforsid 2019
  Atelier: 11 June 2019, Paris, France
  Jérôme Darmont, Natalia Grabar, Olivier Teste, Eds.
  
• March 2019: call for papers for TIA 2019
  Terminologie et intelligence artificielle, common workshop TALN/IC
  Submission deadline: April 10th, 2019 -> April 17th, 2019
  Workshop: July 1st, Toulouse, France
  
• March 2019: annuaires (entreprises, formations, équipes, etc.) de l'association ATALA
• February 2019: DEFT NLP/IR challenge
  Tasks on clinical cases in French: indexing, semantic similarity, information extraction
  Submission of runs: May 9-13th
  Workshop: July 2nd, Toulouse, France
  
• February 2019: Master internship (stage de niveau Master ou ingénieur) Simplification automatique de textes médicaux
  Duration/Durée: 6 months/mois.
• January 2019: Plenary meeting of the CLEAR project at LEPS, Bobigny
• December 2018: Master internship (stage de niveau Master ou ingénieur) Détection automatique de mésusages de médicaments dans les réseaux sociaux
  Duration/Durée: 6 months/mois.
• November 2018: Master internship (stage de niveau Master ou ingénieur) Phonétique pour les besoins cliniques des orthophonistes
  Duration/Durée: 6 months/mois.
• August 2018: Invited talk at Grammarly, Kyiv, Ukraine on Medical text simplification
  Video: https://grammarly.ai/automatic-text-simplification-in-the-biomedical-domain
  
  
• From 2018: Section editor of IMIA Yearbook
  Natural Language Processing section, with Cyril Grouin, LIMSI, France
  
• July 2018: Creation of the SDRC (Syndrome douloureux régional complexe) patient association and of its website.
  Dedicated article by Olivier Clot-Faybesse.
  Orphanet code: ORPHA:99995
  Synonyms (fr): Syndrome douloureux régional complexe, algodystrophie, algoneurodystrophie, Dystrophie sympathique réflexe, Syndrome douloureux régional complexe de type 1, Syndrome douloureux régional complexe de type I
  Synonyms (en): Complex Regional Pain Syndrome Type 1, Reflex Sympathetic Dystrophy, Localized Idiopathic Musculoskeletal Pain Syndrome
  
• July 2018: Plenary meeting of the CLEAR project at LIMSI, Orsay
• July 2018: Inter-MSH article on the ADELP project focused on North-Korean propaganda
  
• June 2018: Participation in the APEC #DigitWeek with the SunRise Smart City project
  
• June 2018: Article on Prix du meilleur papier TALN 2018 by Université de Lille
  
• May 2018: Best paper award for Étude de la lisibilité des documents de santé avec des méthodes d'oculométrie by Natalia Grabar, Emmanuel Farce and Laurent Sparrow presented during CORIA-TALN 2018
  
  
• May 2018: Atelier de l'action ADOC (Entrepôts et analyse de documents) de MADICS dédié à la variété des données SHS, adossé à la conférence Inforsid 2018
  Atelier: 28-31 May 2018, Nantes, France
  Jérôme Darmont, Natalia Grabar, Olivier Teste, Eds.
  
• March 2018: Call for Atelier de l'action ADOC (Entrepôts et analyse de documents) de MADICS dédié à la variété des données SHS, adossé à la conférence Inforsid 2018
  Submission dealine: April 13th, 2018
  Atelier: 28-31 May 2018, Nantes, France
  Jérôme Darmont, Natalia Grabar, Olivier Teste, Eds.
  
• February 26th, 2018: PhD defense of Ornella Wandji Tchami (U de Lille, U de Hildesheim)
  Analyse automatique des verbes dans des textes de corpus médicaux: enjeux théoriques et appliqués
  Advisors: Dany Amiot, U de Lille, France; Ulrich Heid, U de Hildesheim, Germany
  Co-advisor: Natalia Grabar, CNRS, France
  
• December 2017: Master internship (stage de niveau Master ou ingénieur) Modèle pour la fiabilité des informations et des connaissances
  Duration/Durée: 6 months/mois.
• October 2017:
• September 2017: PhD offer Simplification de textes médicaux
  Application deadline: as soon as possible
  Contact: Natalia Grabar
  
• September 2017:
• July 2017: CLEAR (Communication, Literacy, Education, Accessibility, Readability) project accepted within the ANR framework
  Main investigator: Natalia Grabar
  
• July 2017: DEMONEXT (Dérivation Morphologique en Extension) project accepted within the ANR framework
  Main investigator: Fiammetta Namer
  
• March 2017: Master internship (stage de niveau Master ou ingénieur) Perception de villes et objets intelligents
  Duration/Durée: 6 months/mois.
• March 2017: Special Issue - Terminology 24(2), 2018. John Benjamins
  Computational Terminology and Filtering of Terminological Information.
  Submission dealine: June 1st, 2017
  Call for Special issue and submission website
  Patrick Drouin, Natalia Grabar, Thierry Hamon, Kyo Kageura and Koichi Takeuchi, Eds.
• January 2017: Master 2 internship (stage de niveau Master 2) Fouille de bases bibliographiques pour extraire les interactions entre l'alimentation et les médicaments
  Duration/Durée: 6 months/mois.
• Dec 12th, 2016: 5th International Workshop on Computational Terminology COMPUTERM, to be held within the COLING 2016 conference.
  Organizers of the workshop: Patrick Drouin, Natalia Grabar, Thierry Hamon, Kyo Kageura, Koichi Takeuchi.
• October 2016: REM (Vers une nouvelle conception des constructions modales en anglais : des paradigmes basés sur des traits distinctifs à la représentation probabliliste basée sur l’usage) project accepted within the ANR framework, bilateral call France-Suisse
  Main investigators: Ilse Depraetere, Martin Hilpert
  
• September 2016: PhD offer Fouille de texte et extraction d'informations dans les données cliniques
  Application deadline: as soon as possible
  Contact: Vincent Claveau and Natalia Grabar
  
• July 2016: MIAM (Maladies, Interactions Alimentation-Médicaments) project accepted within the ANR framework
  Main investigator: Thierry Hamon
  
• June 2016: 5th International Workshop on Computational Terminology COMPUTERM accepted within the COLING 2016 conference.
  Organizers of the workshop: Patrick Drouin, Natalia Grabar, Thierry Hamon, Kyo Kageura, Koichi Takeuchi.
• June 2016: FigTem project for the bilateral collaboration France-Brazil accepted within the INS2I framework
  Main investigators: Vincent Claveau, Claudia Moro.
• May 2016: ADELP project, dedicated to the analysis of the DPRK English Language Propaganda (2007-2015), accepted within the MESHS Partenariat framework
  Main investigators: Mason Richey, Natalia Grabar
  
• March 2016: PhD offer e-Quality and quality indicators for the medication prescriptions
  Application deadline: May 31, 2016.
• TALN 2016 workshop Risque et TAL: détection, prévention, gestion
  July 4th, Paris, France
• February 2016: BigClin project accepted within the LABEX COMINLABS framework
  Main investigators: Vincent Claveau, Marc Cuggia
• January 2016: Master 2 internship (stage de niveau Master 2) Extraction d'informations pour enrichir les guides touristiques
  Duration/Durée: 6 months/mois.
• January 2016: Master 2 internship (stage de niveau Master 2) Vers la simplification de textes techniques
  Duration/Durée: 6 months/mois.
• 
  Support the INDIEGOGO Crowdfunding campaign launched by Health On the Net and contribute to promoting trustworthy health information online. http://igg.me/at/HONcodeForAll
• December 2015: special issue of Terminology 21(2), 2015. John Benjamins. Patrick Drouin, Natalia Grabar, Thierry Hamon and Kyo Kageura, Eds.
  Terminology across languages and domains
• November 2015: PACHA -- Développement et validation d'indicateurs automatisés de pertinence de la prescription des anticoagulants oraux en médecine adulte à partir du système d'information hospitalier project accepted within the PREPS framework.
  Main investigator: Frantz Thiessart.
• July 2015: Révolutions scientifiques et histoire de la macroéconomie d'hier à aujourd'hui project accepted within the MESHS Projet Emergent framework.
  Main investigator: Goulven Rubin.
• July 2015: Les espaces du patrimoine culturel numérique : topologies et topographies des itinéraires culturels project accepted within the PEPS/Université de Lille framework.
  Main investigator: Marta Severo.
• 22 June 2015: Franco-Ukrainian Forum of Universities (FUFU) in Kyiv, Ukraine
• May 2015: SEPAPH (Segmentation de la parole chez les patients aphasiques) project accepted within the MESHS Emergent framework.
  Main investigator: Anahita Basirat.
• January 2015: SIGSLAV (Special Interest Group on Slavic Natural Language Processing) of ACL is open.
• January 2015: L3/M1 internship (stage de niveau L3/M1) Transcription des conversations téléphoniques
  Duration/Durée: 3 months/mois.
• January 2015: Master 2 internship (stage de niveau Master 2) Analyse de la communication entre les patients et les médecins
  Duration/Durée: 6 months/mois.
• December 2014: Some morphological resources for French medical language/Quelques ressources morphologiques pour le français medical
  
• December 2014: Project EQU (Éthique, Qualité, Urgence) accepted within the Université Lille 3 framework Thématiques de l'Établissement.
  Main investigator: Natalia Grabar
• November 2014: Project TECTONIQ (les TEchnologies de l'information et de la communication au Coeur du TerritOire NumérIQue pour la valorisation du patrimoine : analyse des dispositifs et de leurs usages) accepted within the national framework PEPS.
  Main investigator: Eric Kergosien.
• October 2014: First call for submissions for a special issue of Terminology series dedicated to Terminology across languages and domains (Submission deadline: January 25th, 2015).
  Guest Editors: Patrick Drouin, Natalia Grabar, Thierry Hamon, and Kyo Kageura.
• September 19th, 2014: PhD defense of Marie Dupuch (U Paris 6)
  Détection de termes sémantiquement proches : clustering non supervisé basé sur les relations sémantiques et le degré d'apparenté sémantique
  Advisor: Marie-Christine Jaulent, INSERM, Paris, France
  Co-advisor: Natalia Grabar, CNRS, France
  
• August 2014: 4th International Workshop on Computational Terminology COMPUTERM held with the COLING 2014 conference.
  Organizers of the workshop: Patrick Drouin, Natalia Grabar, Thierry Hamon, and Kyo Kageura.
  Website of the workshop.
  Proceedings of the workshop.
• May 2014: PhD proposal (proposition de sujet de thèse)
• February 2014: First call for the 4th International Workshop on Computational Terminology COMPUTERM accepted and to be held with the COLING 2014 conference.
  Organizers of the workshop: Patrick Drouin, Natalia Grabar, Thierry Hamon, and Kyo Kageura.
  Website of the workshop.
• January 2014: Master internships (stages de Master)
• December 2013: Patients' mind project accepted within the national framework inter-MSH
  Main investigator: Sandra Bringay
• October 2013: POMELO project accepted within the framework Projets Émergents de la MESHS (Maison européenne des sciences de l'homme et de la société)
  Main investigator: Natalia Grabar
• 12-13 September 2013: Conference Morphology and its interfaces in Lille
• May 2013: project Amélioration de la gestion du risque médicamenteux accepted within the framework of Université Lille 3
• December 2012: project Parlons de nous accepted within the framework MSH Montpellier
  Main investigator: Sandra Bringay
• November 2012: Publication of the special issue of the Applied Ontology journal Terminologies and ontologies: continuum or dichotomy: Volume 7, Number 4 / 2012
• September 2012: Call for submissions to the conference Morphology and its interfaces. To be held in Lille, France on September 12-13, 2013
• 28/08/2012: Workshop MIE Computational Methods in Pharmacovigilance, in Pisa, Italy
• May 2012: Organization of the workshop MIE Computational Methods in Pharmacovigilance. To be held on 28/08/2012 in Pisa, Italy
• 23/04/2012: Workshop EACL Innovative hybrid approaches to the processing of textual data Workshop website.
• February 2012: project SKATE, accepted within the BQR framework of the Université Lille1&3
  Main investigators: Natalia Grabar, Fayssal Tayalati, Cédric Patin
• Organization of the workshop EACL Innovative hybrid approaches to the processing of textual data Workshop website. To be held on 23/04/2012 in Avignon, France
• 25/11/2011: Launching of the project CoMeTe: kick-off meeting held at MESHS, Lille
• September 2011: project CoMeTe accepted within the framework Projets Émergents de la MESHS (Maison européenne des sciences de l'homme et de la société)
  Main investigator: Natalia Grabar
• July 2011: project Ravel accepted within the framework TecSan ANR (Agence Nationale de Recherche)
  Main investigator: Marc Cuggia
• July 2011: project DICO-Risque (Développement d'une boite à outils pour l'analyse de l'incertitude et de la qualité de la connaissance, dans les évaluations des risques des perturbateurs endocriniens: application à l'étude de cas du Biphenol-A) accepted within the framework PNRPE (Programme National de Recherche sur les Perturbateurs Endocriniens du Ministère de l'Écologie, du Développement durable, des Transports et du Logement)
  Main investigator: Laura Maxim
• July 2011: Beginning of the project REACH: Expertise dans l'évaluation réglementaire des risques chimiques, accepted within the framework PIR (Programme Interdisciplinaire de Recherche du CNRS)
  Main investigator: Laura Maxim
• May 2011: Beginning of the project Scientific Research Network (WOG) Contrastive Linguistics: constructional and functional approaches, accepted within the framework of the Research Foundation - Flanders (FWO)
• November 2010: Organization of a special issue of the Applied Ontology : Terminologies and ontologies: continuum or dichotomy.
  web site of the special issue (issue planned for the summer 2012)