User Tools

Site Tools

Agence Nationale de la Recherche

start

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
start [2014/02/27 18:26]
carlos.ramisch
start [2017/09/15 16:29] (current)
carlos.ramisch
Line 1: Line 1:
-====== Wiki TALEP ======+====== PARSEME-FR ======
  
-Bienvenue sur le wiki de l'équipe TALEP (Traitement automatique du langage écrit et parlé) du LIF (Laboratoire d'Informatique Fondamentale de Marseille).+Welcome to the official website of [[http://www.agence-nationale-recherche.fr/|ANR]] project PARSEME-FR
  
-Ce wiki est un complément de [[notre page web oficielle|www.lif.univ-mrs.fr/recherche/equipes/6/]] sur le site du LIF. Il contient des informations internes concernant nos projetsréunionsséminairesdocumentation, sujets de stage, etc. Il contient une partie publique et une partie "Intranet" à laquelle seulement les mebres de l'équipe peuvent accéder.+The PARSEME-FR project aims at improving linguistic representativeness, precision, robustness and computational efficiency of Natural Language Processing (NLP) applications, notably parsing of FrenchThe project focuses on a major bottleneck of these applications: MultiWord Expressions (MWEs), that is, groups of words that must be treated as units at some level of linguistic processing, such as //hot dog//, //hard disk////kick the bucket////United Nations// and //pay attention//.
  
-Ce wiki est actuellement en phase de testContactez CRamisch si vous avez des questions.+Despite recent advances, the state of the art concerning MWE representation and processing is largely unsatisfactoryCurrent research concentrates either on creating MWE lexicons or on the automatic recognition of MWEs in running textOnly few approaches address the links between MWEs and a comprehensive linguistic analysis of text. These approaches confirm that a proper MWE treatment increases both linguistic precision and robustness of NLP systems. They are, however, mostly limited to specific MWE classes and syntactic parsing. This unsatisfactory state is mainly due to the lack of linguistic knowledge bases encoding MWE information, that could be fed into linguistic analyzers. In French, such resources exist, but are incomplete in terms of syntactic and semantic representation, coverage and adequacy to NLP tools. 
 + 
 +We propose to bridge the gap between linguistic precision and computational efficiency in NLP applications by investigating the syntactic and semantic representation of MWEs in language resources, the integration of MWE analysis in syntactic parsing and its links to semantic processing. Expected deliverables include enhanced language resources (lexicons, grammars and annotated corpora), MWE-aware statistical and symbolic parsers and tools linking predicted MWEs to knowledge bases. This proposal is a spin-off of [[http://parseme.eu|PARSEME]], an European IC1207 [[http://www.cost.eu/|COST]] action on the same topic.
start.1393521969.txt.gz · Last modified: 2014/02/27 18:26 by carlos.ramisch