D Annexe: curriculum vitae des membres du
projet
D.1 Éric de la Clergerie (ATOLL / INRIA)
Éric de la Clergerie
defended his PhD in 1993 and is now Research Officer (CR) at
INRIA. Since 2002, he is the
scientific leader of project-team ATOLL (Sotware Tools for Natural
Language Processing). His researches focus on the development of
parsing techniques for several grammatical formalisms. With
ATOLL, he also got involved
in the development of wide coverage linguistic resources for
French (lexicon, grammar), exploited during the parsing
evaluation campaign EASy/EVALDA.
He has participated to several national actions
(Technolangue/Normalangue-RNIL & Evalda-EASy; ACI MD
Biotim;
INRIA ARCs RLT, GENI &
MOSAIQUE; ILF Lexsynt). In particular, he was
coordinator for RLT and is
co-coordinator for LexSynt. He is also involved in
the international standardization efforts within ISO TC37 SC4
where he is the editor of the MAF proposal (Morpho-syntactic
Annotation Framework, CD 24611), has actively contributed to the
FSR proposal (Feature Structure Representation), and has acted as
head of the French delegation for several international ISO
meetings.
Éric de la Clergerie is also a member of the editorial
committee of the French review T.A.L. (Traitement Automatique des
Langues) and was guest editor of this review for a thematic issue
on “Evolutions in Parsing”.
References
- [9]
- Trouver le coupable :
Fouille d'erreurs sur des sorties d'analyseurs
syntaxiques. In Proc. of TALN'06, pages
287–296, 2006. Prix du meilleur papier,
Benoît Sagot and Éric Villemonte de la Clergerie.
[URL]
- [14]
- Comment obtenir plus des
méta-grammaires. In Proceedings of
TALN'05, Dourdan, France, June 2005. ATALA.
François Thomasset and Éric Villemonte de la
Clergerie.
[URL]
- [20]
- Chaînes de
traitement syntaxique. In Proceedings of
TALN'05, pages 103–112, Dourdan, France, June 2005.
ATALA.
Pierre Boullier, Lionel Clément, Benoît Sagot, and
Éric Villemonte de la Clergerie. [URL]
Pierre Boullier is a
Research Director (DR) at INRIA
and a member of project-team ATOLL. He is a world-wide recognized
specialist in parsing and has developed Syntax, a very efficient parser
compiler for CFGs that has been extended to handle Lexical
Functional Grammars (LFGs), resulting in the Sxlfg parser compiler. An LFG
parser for French built with a preliminary version of
Sxlfg was exploited
during the parsing evaluation campaign EASy.
References
- [7]
- Analyse syntaxique
profonde à grande échelle: SxLFG.
Traitement Automatique des Langues (T.A.L.), 2005. to
appear,
Pierre Boullier and Benoît Sagot.
- [27]
- Efficient and robust LFG
parsing: SxLfg. In Proceedings of IWPT'05,
pages 1–10, Vancouver, Canada, October 2005.
Pierre Boullier and Benoît Sagot. [URL]
- [20]
- Chaînes de
traitement syntaxique. In Proceedings of
TALN'05, pages 103–112, Dourdan, France, June 2005.
ATALA.
Pierre Boullier, Lionel Clément, Benoît Sagot, and
Éric Villemonte de la Clergerie. [URL]
- CNRS September 2002 to present, Research
Engineer in the Language, Information and Representation group
of the Human-Machine Communication Department, where my
activities have regained their previous focus on basic Natural
Language Processing (POS tagging, parsing), particularly in the
context of evaluation, but now address also machine
understanding (human-machine dialog) and language emergence in
communities of artificial autonomous entities .
- Limsi - CNRS July 1997 to September 2002
Research Engineer in the Spoken Language Processing group of
the Human-Machine Communication department where I have been
involved in the DISC DISC European project (best practice in
Spoken Language Dialog System Engineering), the ELSE
preparatory action (crafting of a generic blue print for
evaluating Natural Language Processing Systems using a
semi-automatic quantitative black-box approach), the CLASS
project and in the following national projects: GRACE, MULTITAG
(production of a tagged corpus of 1 million words from the
GRACE
results, in coordination with the CLIFF project), SILFIDE,
TECHNOLANGUE scientific committee.
- INaLF - CNRS - November 1993 to June
1997 Research engineer at Institut National de la Langue
Francaise (INaLF) a unit of Centre National de la Recherche
Scientifique (CNRS). My activities there included some system
administration but dealt mainly with dictionary
computerization, graphic interfaces design and implementation,
evaluation of Part Of Speech taggers (coordinator of the french
GRACE
action), as well as building, management, automatic analysis
and distribution (WWW access) of large text corpora. Contribued
to the French Corpus task of the European project
LE2-4017-LE-PAROLE, after having participated to the
preparatory project PAROLE (MLAP-63-386).
- Rouen University, Lecturer at
Laboratoire d'Informatique de Rouen (LIR)-
October 1992 to September 1993.
- University of Pennsylvania, Invited
researcher - July 1992 to September 1992.
- Computers Communications and Visions
(c2v), Research Engineer - February 1992 to May 1992.
- BULL SA FRANCE, Software Engineer -
October 1991 to December 1991.
- Rouen University, Lecturer at
Laboratoire d'Informatique de Rouen (LIR)-
February 1991 to September 1991.
- University of Pennsylvania,
Post-doctoral research. February 1990 to December 1990.
- University Malaya, Kuala Lumpur,
Malaysia, Lecturer - November 1986 to December 1987.
D.4 Anne Vilnat (LIR
/ LIMSI)
Anne Vilnat, is Maître de
Conférences (HDR) at University Paris Sud since January
1988 and was in charge of the research topic “Analysis
Processes, Generation and Dialogue” of the LIR group of
LIMSI-CNRS, up to June 2005. She has already co-directed 6 PhD.
thesis and has got her “Habilitation à diriger les
recherches” in December 2005. Her memoire is entitled
“Dialogue et analyse de phrases”. She got her PhD. in
Computer Science from University Paris 6 in 1984 and since has
made 73 scientific publications. She participated in the
organizationof the EASY evaluation campaign, for which she
designed the reference formalism. Her most recent publications
include:
- Brigitte Grau, Olivier Ferret, Martine
Hurault-Plantet, Laura Monceaux, Isabelle Robba, Anne Vilnat,
Christian Jacquemin,
Coping with Alternate Formulations of Questions and Answers,
chapitre dans Advances in Open-Domain Question-Answering,
Strzalkowski & Harabagiu (eds), Series Text, Speech and
Language Technology, Vol.32, Springer, Juillet 2006.
- Patrick Paroubek,
Isabelle Robba, Anne Vilnat et Christelle Ayache,
Data, Annotations and Measures in EASY, the Evaluation
Campaign for Parsers of French, LREC 2006, Gênes,
Italie, Mai 2006.
- Christelle Ayache, Brigitte Grau et Anne
Vilnat,
EQueR : the French Evaluation Campaign of Questions
Answering Systems LREC 2006, Gênes, Italie, Mai
2006.
- Brigitte Grau, Anne-Laure Ligozat,
Isabelle Robba, Anne Vilnat et Laura Monceaux
FRASQUES: A Question-Answering System in the EQueR
Evaluation Campaign LREC 2006, Gênes, Italie, Mai
2006.
- Anne-Laure Ligozat, Brigitte Grau,
Isabelle Robba et Anne Vilnat
Evaluation and Improvement of Cross-Lingual Question
Answering Strategies, WS MLQA de EACL 2006, Trento,
Italie, Mai 2006.
- Brigitte Grau, Anne-Laure Ligozat,
Isabelle Robba, Anne Vilnat,
Term Translation Validation by Retrieving Bi-terms,
LNCS, (Version étendue du WS Clef 05) 2006.
- Anne-Laure Ligozat, Brigitte Grau,
Isabelle Robba et Anne Vilnat
L'extraction des réponses dans un système de
question-réponse, TALN, Leuven, Avril 2006.
- Anne-Laure Ligozat, Brigitte Grau,
Isabelle Robba et Anne Vilnat
Question-Réponse multilingue : évaluation et
amélioration des stratégies de changement de
langue, CORIA, Lyon, Mars 2006.
D.5 Isabelle Robba (LIR
/ LIMSI)
Isabelle Robba is Maître de
Conférences at IUT d'Orsay where she teaches basic
Computer Science. She got her PhD. in Computer Science from
University Paris Sud in 1992. The title is “L'étude
des mécanismes de raisonnement par analogie dans l'analyse
de phrase: le système MIRA”. She was involved in the
EASY evaluation campaign as an organizer and worked more
particulary on the evaluation protocole and reference
annotations.
Her most recent publications include:
- Anne Vilnat, Patrick Paroubek, Laura
Monceaux, Isabelle Robba, Véronique Gendner, Gabriel
Illouz, Michèle Jardino,
The Ongoing Evaluation Campaign of Syntactic Parsing of
French: EASY, actes de la Fourth International Conference
on Language Resources and Evaluation (LREC), Lisboa, May 2004,
vol. 6, pp 2023-2026.
- V. Gendner, G. Illouz, M. Jardino, L.
Monceaux, P. Paroubek, I. Robba, A. Vilnat
PEAS, the first instanciation of a comparative framework
for evaluating parsers of French, actes de la 10th
Conference of The European Chapter of the Assciation for
Computational Linguistics, Budapest, Hungary, April 12-17 2003,
Companion Volume, pp 95-98.
- Véronique Gendner, Gabriel
Illouze, Michèle Jardino, Laura Monceaux, Patrick Paroubek,
Isabelle Robba, Anne Vilnat
A Protocol for Evaluating Analyzers of Syntax (PEAS)
in Proceedings of the Third International Conference on
Language Ressources and Evaluation (LREC), Las Palmas de Gran
Canaria, Spain, May 27th-June 2nd 2002, vol 2, pp 590-597
Claire Gardent graduated in linguistics at the University of
Toulouse in 1986, obtained an MSc in Artificial Intelligence from
the University of Essex in 1987 and defended a PhD in Cognitive
Science at the University of Edinburgh in 1991. From 1991 to
2000, she worked as a researcher for the Universities of Utrecht
and Amsterdam (The Netherlands), Clermont-Ferrand (France) and
Sarrebruecken (Germany). Since 2000, she is a Chargée de
Recherche de 1ère classe at the CNRS.
Claire Gardent's research focuses on the computational treatment
of natural language meaning i.e., on computational semantics. She
has worked on the role of inference in Natural Language
Processing (NLP) and is currently focusing on developing a
computational infrastructure for the semantic treatment of
French.
Claire Gardent has published a book on analysis and generation
(with Karine Baschung) and about 50 articles in (mainly
international) journals and conference proceedings. She has been
nominated Chair of the European Chapter for the Association of
Computational Linguistics, editor in chief of the french journal
"Traitement Automatique des Langues" and member of the editorial
board of the journals "Computational Linguistics", "Journal of
Semantics". Each year she is on the programme committee for half
a dozen international conferences or workshops. She also acted as
scientific chair for various international conferences, workshops
and summer schools (e;g., ESSLLI, the European Summer School for
Logic, Language and Information).
References
- [4]
- Création d'un
corpus annoté pour le traitement des descriptions
définies. Traitement Automatique des
Langues, 46(1), 2005.
C. Gardent and H. Manuélian.
- [6]
- Extracting
subcategorisation information from Maurice Gross' grammar
lexicon. Archives of Control Sciences,
15(LI):253–264, 2005.
C. Gardent, B. Guillaume, G. Perrier, and
I. Falk.
- [16]
- Large scale semantic
construction for tree adjoining grammar. In
Proceedings of Logical Aspects in Computational
Linguistics, Bordeaux, France, 2005.
C. Gardent and Y. Parmentier.
Since
1988, Azim Roussanaly is Assistant Professor (Maître de
conférences) at University Nancy2 and a member of the
“Langue et Dialogue” project-team at LORIA . He
conducts his researches in the area of the Natural Language
Processing (NLP) and, for the last years, his works are mainly
focused on parsing techniques especially for the Lexicalized Tree
Adjoining Grammars (LTAG) formalism in the context of a wide
coverage French grammar. He has developed LLP2, a LTAG-based
parser for French which was exploited during the parsing
evaluation campaign EASy.
References
- [32]
- Représentation et
gestion de grammaires TAG. Traitement Automatique
des Langues (T.A.L.), 2004.
B Crabbé, B Gaiffe, and
A. Roussanaly.
- [33]
- Premier bilan de la
participation du LORIA à la campagne d'évaluation
EASy. In Proceedings of TALN'05 EASy Workshop,
Dourdan, France, June 2005. ATALA.
A. Roussanaly, B. Crabbé, and
J. Perrin.
- [34]
- A new metagrammar
compiler. In TAG+6 (International Workshop on Tree
Adjoining Grammars and Related Frameworks), Venice, Italy,
May 2002.
B Crabbé, B Gaiffe, and
A. Roussanaly.
D.8 Gaël de Chalendar (LIC2M /
CEA-LIST)
Gaël de Chalendar is a
researcher at CEA in Laboratoire d'Ingénierie de la
Connaissance Multimédia Multilingue (LIC2M) CEA-LIST, Centre de Fontenay-aux-Roses.
Gael got his PhD. in computer science in 2001 from University of
Paris Sud. The title is: “Généralisation de
Graphes Conceptuels à l'aide d'Heuristiques et
Apprentissage de Relations Sémantiques entre
Concepts”. From 2001 to 2002, Gael was Attaché
Temporaire d'Enseignement et de Recherche at IUT d'Orsay where he
tought basic computer science and natural language
processing.
Publications:
- Romaric Besançon et Gaël de
Chalendar (2005)
L'analyseur syntaxique de LIMA dans la campagne
d'évaluation EASY, Actes de la 12ème
conférence annuelle sur le Traitement Automatique des
Langues Naturelles (TALN 2005), 6-10 juin 2005, Dourdan,
France.
- Romaric Besançon, Gaël de
Chalendar, Olivier Ferret, Christian Fluhr, Olivier Mesnard et
Hubert Naets (2004)
Concept-Based Searching and Merging for Multilingual
Information Retrieval: First Experiments at CLEF 2003, 4th
Workshop of the Cross- Language Evaluation Forum, Springer
Verlag.
- Gaël de Chalendar, Tiphaine Dalmas,
F. Elkateb-Gara, Olivier Ferret, Brigitte Grau, Martine
Hurault-Plantet, Gabriel Illouz, Laura Monceaux, Isabelle
Robba, Anne Vilnat (2002)
The Question Answering System QALC at LIMSI,
Experiments in Using Web and WordNet. TREC 2002.
- Gaël de Chalendar, Brigitte Grau
and Olivier Ferret (2000)
A cost-bounded algorithm to control events generalization,
in Conceptual Structures : Logic, Linguistic, and Computational
Issues. 8th International Conference on Conceptual
Structures ICCS, Springer, Bernhard Ganter and Guy W. Mineau
editors, Lectures Notes in Artificial Intelligence, vol. 1867,
pages 555-568
- Gaël de Chalendar and Brigitte Grau
(2000)
SVETLAN' or how to Classify Words using their Context,
Proceedings of the 12th International Conference on Knowledge
Engineering and Knowledge Management, EKAW 2000, Springer, Rose
Dieng and Olivier Corby eds., Lectures notes in artificial
intelligence vol. 1937, pages 203-216
D.9 Olivier Ferret (LIC2M /
CEA-LIST)
Olivier Ferret is a
researcher at CEA in the Laboratoire d'Ingénierie de la
Connaissance Multimédia Multilingue (LIC2M) CEA-LIST, Centre de Fontenay-aux-Roses.
He got his PhD. in computer science in 1998 from University Paris
Sud. The title is: “ANTHAPSI : un système d'analyse
thématique et d'apprentissage de connaissances
pragmatiques fondé sur l'amorçage”. From 2000
to 2001, he did a post-doc at Direction des Technologies de
l'Information of CEA, in the context of the PRISME project about
information filtering. In 1999 he was research engineer in AEGIS
company for the project Eurêka PVS 98 about multi-agent
based flexible information systems.
Publications:
- Olivier Ferret (2004)
Discovering word senses from a network of lexical
cooccurrences, COLING 2004, Genève.
- Sana Châar, Olivier Ferret et
Christian Fluhr (2004)
Filtrage pour la construction de résumés
multi-documents guidée par un profil, revue TAL.
Olivier Ferret (2002) Using collocations for topic segmentation
and link detection, COLING 2002, Tapei.
- Olivier Ferret et Brigitte Grau
(2002)
A Bootstrapping Approach For Robust Topic Analysis,
Journal of Natural language Enginering (NLE), Special issue on
robust methods of corpus analysis.
- O. Ferret, B. Grau, M. Hurault-Plantet,
G. Illouz, C. Jacquemin, L. Monceaux, I. Robba, A. Vilnat
(2002)
How NLP Can Improve Question Answering, Knowledge
Organization, Vol. 29, N°3-4, p. 135-155
D.10 Gil Francoploulo
Gil
Francopoulo got a PhD thesis at University Paris-6 in 1988 on
"induction of grammar rules" at CNRS-LIMSI laboratory. He works
in lexicon management, sentence parsing and search engines for 20
years: 4 years as Tagmatica Director (www.tagmatica.com), 12
years for LexiQuest (formely ERLI and GSI-ERLI) and 4 years for
various banks and software companies. He was co-author of the
Genelex lexicon model in 1991 and managed the five languages
lexicons within LexiQuest. He participated in several National
and International projects (Eureka/Genelex, Eagles,
eContent/LIRICS,
Technolangue/Normalangue-RNIL, Evalda-Easy, ILF Lexsynt). Currently, he is editor
of the ISO standard for the lexicons dedicated to Natural
Language Processing (aka Lexical Markup Framewrok, LMF). He is
convenior of the ISO group for the management of morpho-syntactic
data categories within ISO-12620 revision. He participates in the
work in progress about SynAF (ISO WD24615). He is liaison officer
between ISO-TC37/SC4 and W3C.
Recent Publications :
- Francopoulo G., George M. Lexical
Markup Framework. ISO-CD24613 rev-9. 2006 ISO Geneva.
- Francopoulo G., George M., Calzolari N.,
Monachini M., Bel N., Pet M., Soria C. Lexical Markup
Framework (LMF). LREC-2006
- Francopoulo G., Declerck T., Monachini
M., Romary L. The relevance of standards for research
infrastructures. LREC-2006
- Romary L., Salmon-Alt S., Francopoulo G.
Standards going concrete: from LMF to Morphalou.
COLING-2004 workshop Enhancing and using electronic
dictionaries.
Eric de la
Clergerie