Seminaire: CLI, R. Mitkov et F. Cornish, Resolution d'anaphore, 11 Dec. 2007

[Thierry Hamon]

Date: Wed, 5 Dec 2007 15:14:18 +0100
From: Thierry Poibeau <Thierry.Poibeau at lipn.univ-paris13.fr>
Message-Id: <63ffb6e6130dd144f100a46a052fb032 at lipn.univ-paris13.fr>
X-url: http://pers-www.wlv.ac.uk/~le1825/
X-url: http://w3.univ-tlse2.fr:8880/erss/index.jsp?perso=cornish&subURL=index.html
X-url: http://www-lipn.univ-paris13.fr/RCLN/CLI/
X-url: http://www-lipn.univ-paris13.fr/RCLN/Seminaire/


Nous avons le plaisir d'annoncer la reprise des séminaires
"Connaissances, Langue et Informatique".


               Laboratoire d'Informatique de Paris-Nord
                           Institut Galilée

       Les après-midis "Connaissances, Langue et Informatique"
                          Séminaires en duo

               Ruslan Mitkov *   -   Francis Cornish **

   * Université de Wolverhampton, UK, http://pers-www.wlv.ac.uk/~le1825/
  ** Université toulouse-Le Mirail,
http://w3.univ-tlse2.fr:8880/erss/index.jsp?perso=cornish&subURL=index.html

            *** La résolution d'anaphore, théorie et applications ***
                   Anaphora resolution: theory and applications
                 (les exposés et la discussion seront en anglais)

                    Mardi 11 décembre 2007, de 14h à 17h.

                       à l'Université Paris-Nord
                       Institut Galilée, amphi Euler
                         Campus de Villetaneuse
               http://www-lipn.univ-paris13.fr/RCLN/CLI/

(Pour plus d'information concernant les orateurs, le lieu du séminaire
et les moyens d'accès, voir la page web ci-dessus ; le bâtiment
Galilée correspond à la lettre G sur le plan de l'université)

------------------------------------------------------------------------


Résumé des exposés

Francis Cornish
Anaphora: Text-based, or discourse-dependent?

The traditional definition of anaphora in purely co-textual terms as a
relation between two co-occurring expressions is still in wide
currency in studies of the phenomenon. Under this conception, the
anaphor, a referentially-dependent expression type, requires
"saturation" by an appropriate fully autonomous, lexically-based
expression, the antecedent, in order to achieve full sense and
reference. However, this definition needs to be re-examined in the
light of the ways in which real texts operate and are understood,
where the resulting picture is rather different. This is my major goal
in the talk to be presented.  The talk will start by characterizing
two opposing approaches to the study of anaphora as well as deixis --
the textualists' and the discourse-functionalists' -- and will go on
to develop a discourse-functional approach to both of these
discourse-referring procedures, arguing for its validity. I aim to
show that it is only in terms of a dynamic interaction amongst the
complementary dimensions of text and discourse, as well as context,
that the true complexity of anaphoric reference may be satisfactorily
described.


Ruslan Mitkov
Anaphora resolution: to what extent does it help NLP applications?

Research in anaphora resolution has focused almost exclusively on the
intrinsic evaluation of the algorithm/system and not on the issue of
extrinsic evaluation. In the context of anaphora resolution, extrinsic
evaluation is concerned with the impact of an anaphora resolution
module on a larger NLP system of which it is part. In this
presentation I shall discuss whether the well-known anaphora
resolution system MARS (Mitkov et al. 2002) can improve (and if it
can, to what extent?) or not the performance of three NLP
applications: text summarisation, term extraction and text
categorisation..


http://www-lipn.univ-paris13.fr/RCLN/Seminaire/


-------------------------------------------------------------------------
Message diffuse par la liste Langage Naturel <LN at cines.fr>
Informations, abonnement : http://www.atala.org/article.php3?id_article=48
English version       : 
Archives                 : http://listserv.linguistlist.org/archives/ln.html
                                http://liste.cines.fr/info/ln

La liste LN est parrainee par l'ATALA (Association pour le Traitement
Automatique des Langues)
Information et adhesion  : http://www.atala.org/
-------------------------------------------------------------------------