Séminaire Alpage (lundi 4 mai) Jennifer Foster

[bcrabbe at LINGUIST.JUSSIEU.FR]

******************* Séminaire Alpage *******************

        Séminaire de l'école doctorale de Paris 7

Il s'agit du séminaire de recherche en linguistique informatique
organisé par l'équipe Alpage, Alpage est une nouvelle équipe mixte
Inria -- Paris 7 issue de la fusion des équipes Atoll et Talana.
L'équipe centre ses intérêts scientifiques autour de l'analyse
syntaxique automatique et du traitement du discours pour la langue
française.

Le séminaire se tient le lundi de 14.00 à 16.00 tous les 15 jours.
Il a lieu en salle 131 au 30 rue du Château des Rentiers 75013 Paris
(premier étage)

Toute personne intéressée est la bienvenue.

***********************************************************

Lundi 4 mai 2009, Jennifer Foster (Dublin) nous parlera de :

Detecting and Parsing Ungrammatical Text

Given the human propensity to err, a parser must be able to produce
accurate analyses for sentences which are deviant according to human
standards, yet which we routinely interpret correctly. State-of-the-
art statistical parsers are generally robust to errors, and they
will return analyses for most ungrammatical sentences. However, these
robust analyses are not necessarily correct because they do not always
reflect the meanings of the ill-formed sentences. I present a two-
stage "error-aware" statistical parsing architecture which uses  two
versions of a statistical parser, one trained on a normal treebank
and the other trained on an automatically created ungrammatical version
of the original treebank. A binary classifier is used to decide which
version to employ. I present the results of experiments carried out using this
parsing architecture and the Penn Treebank. I also present the results of
experiments carried out with various grammatical/ungrammatical classifiers, and
I present a tool called GenERRate which can be used to automatically create
ungrammatical training data.

Séminaires à venir :

18/5 : J.P. Prost (Orléans)



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/parislinguists/attachments/20090429/4b982603/attachment.htm>