Accueil du site Accueil du site Adhésion Contact Plan du site

Machine Learning for NLP

Volume 50 numéro 3.

Direction : Isabelle Tellier and Mark Steedman.

The TAL journal proposes a call for papers on the subject of "Machine Learning for NLP". Machine Learning is the study of algorithms that allow computer programs to automatically improve through experience (definition proposed by Tom Mitchell in his "Machine Learning" book). This domain has drastically increased in the last few years, and its interactions with NLP are more and more tight and frequent.

From a linguistic point of view, the interests for this evolution are numerous. As a matter of fact, manually built resources are time-consuming and expensive, and the process must be started again for each distinct language and each distinct sub-domain of a language. Machine Learning offers an attractive alternative, allowing to obtain or improve at a lower cost such a resource, with better guarantees of robustness and coverage. The inductive approach, used for a long time in the "corpus linguistic" community, can now be operationalized at a large scale, and its results be rigorously tested. And formal theories of learning also contribute to the long-standing debate about natural language acquisition.

From a Machine Learning point of view, NLP is a rich application domain where problems are numerous and difficult, and for which many data are usually available. But the interpretability of the obtained results is often problematic. More and more subtle specialist-reserved mathematical device are used : in this context, is linguistics still useful ? What confidence can a linguist have on the result of a Machine Learning system ?

A number of the electronic review TAL will be dedicated to this theme. Beyond reports about yet another experiment applying a special Machine Learning method on a special linguistic task, more general theoretical and methodological reflexions are encouraged. For each contribution and each method used, a special effort should be made to clarify what are the linguistic as well as computational underlying hypotheses.

The Machine Learning approach considered can be :
-  either theoretical, concerning learnability/non learnability results for classes of objects, with respect to formal criteria
-  either empirical, based on an experimental protocol exploiting annotated (in the case of supervised learning) or not annotated (in the case of non supervised learning) data

The methods used can be :
-  symbolic (grammatical inference, ILP...)
-  based on probabilistic (either generative or discriminative) models
-  based on similarities (neighboring, analogy, memory-based learning...)

Application domains can be :
-  acquisition or improving of resources (including automata, grammars, sub-categorisation frames, concept-based ontologies...)
-  speech analysis
-  corpus labeling (either lexical, syntactic, functional, thematic, semantic...)
-  clustering and classification of texts (according to various possible criteria : author, content, opinion...)
-  information extraction (including : extraction and typing of named entities)
-  question/answering systems
-  automatic summarization
-  machine translation

Guest Editors:

-  Isabelle Tellier, LIFO, University of Orléans
-  Mark Steedman, ICCS, University of Edinburgh, Scotland

Practical issues:

Contributions (25 pages maximum, PDF format) must be sent by e-mail to the following address: (isabelle dot tellier at univ dash orleans dot fr) Style sheets are available here. Language: manuscripts may be submitted in English or French. French-speaking authors are requested to submit in French.

Important dates
-  01/07/2009 Detailed summary (1p)
-  06/07/2009 Deadline for submission.
-  04/09/2009 Notification to authors.
-  02/10/2009 Deadline for submission of a revised version.
-  10/11/2009 Final decision.
-  February 2010 publication on line.

Scientific commitee :
-  Pieter Adriaans, HSC Lab, University of Amsterdam, Netherlands
-  Massih Amini, LIP6, Paris and ITI-CNRC, Canada
-  Walter Daelemans, CNTS, University of Anvers, Belgium
-  Pierre Dupont, university of Louvain, Belgium
-  Alexander Clark, Royal Holloway, University of London, Great-Britain
-  Hervé Dejean, Xerox Center, Grenoble
-  George Foster, National Research Council, Canada
-  Colin de la Higuera, Laboratoire Hubert Curien, University of St Etienne
-  François Denis, LIF, University of Marseille
-  Patrick Gallinari, LIP6, University of Paris 6
-  Cyril Goutte, National Research Council, Canada
-  Laurent Miclet, Enssat, Lannion
-  Richard Moot, Labri/CNRS, Bordeaux
-  Emmanuel Morin, LINA, University of Nantes
-  Jose Oncina, PRAI Group, University of Alicante, Spain
-  Pascale Sébillot, IRISA, INSA, Rennes
-  Marc Tommasi, LIFL-Inria, University of Lille
-  Menno van Zaanen, ILK, University of Tilburg, Netherlands

Date de dernière mise à jour : 11 July 2009, auteur : Rédacteurs en chef.