mardi 10 septembre 2013

Exposés de Mark Johnson

Un des meilleurs spécialistes mondiaux de linguistique computationnelle, Mark Johnson, va donner deux exposés à l'université Paris Diderot. Tous les étudiants intéressés par le traitement automatique des langues son fortement invités à y assister:

*Language acquisition as statistical inference**
**Mark Johnson**
**Macquarie University**
**noon, 12th September, LingLunch*

  Linglunch Paris Diderot
  Thursday, 12th septembre 2013
  12h-13h, salle 103
  bâtiment Olympe de Gouges
  (8) rue Albert Einstein, 75013

This talk argues that language acquisition -- in particular, syntactic
parameter setting -- is profitably viewed as a statistical inference
problem.  I discuss some issues associated with statistical inference
that linguists might be concerned about, including the possibility of
"Zombie" parameter settings.  The bulk of the talk focuses on estimating
parameters in a Stabler-style Minimalist Grammar framework.  Building on
recent results of Hunter and Dyer (2013), we show how estimating weights
associated with lexical entries -- including the empty functional
categories that control parametric syntactic variation -- can be reduced
to estimating weights in what appears to be a new grammar formalism
called "feature-weighted context-free grammars", which is a MaxEnt
generalisation of the "tied context-free grammars" of Headden et al
(2009).  Importantly, the partition function and its derivatives of a
feature-weighted context-free grammar can be calculated using a
generalisation inspired by the Inside-Outside algorithm of the
algorithms for calculating partition functions in Nederhof and Satta
(2009).  We show how this can be used to learn lexical entries and verb
movement and XP movement parameters in three toy corpora.

*Grammars and Topic Models**
**Mark Johnson**
**Macquarie University**
**11am, 20th September, Alpage Group*

  Séminaire ALPAGE
  Friday, 20th september, 11h-12h30
  salle 127
  bâtiment Olympe de Gouges
  (8) rue Albert Einstein, 75013

Context-free grammars have been a cornerstone of theoretical computer
science and computational linguistics since their inception over half a
century ago.  Topic models are a newer development in machine learning
that play an important role in document analysis and information
retrieval.  It turns out there is a surprising connection between the
two that suggests novel ways of extending both grammars and topic
models.  After explaining this connection, I go on to describe
extensions which identify topical multiword collocations and
automatically learn the internal structure of named-entity phrases.
These new models have applications in text data mining and information

Cette série d'exposés est financée par:
Research in Paris Programme - Mairie de Paris                                                      
Ecole Normale Supérieure                                                                           
Ecole des Hautes Etudes en Sciences Sociales                                                       
Fondation Pierre Gilles de Gennes

Aucun commentaire:

Enregistrer un commentaire