Manual thematic annotation of a journalistic corpus : first observations and evaluation. The work presented in this paper focuses on the creation of a corpus of journalistic texts annotated at dicourse level, more precisely on a topic level. The annotation model is a classic segmentation one, to which we add transition zones between topical units. We assume that in a well-structured text, the a...

This article details the results of analyses we conducted on the discourse of schizophrenic patients, at the oral production (disfluences) and lexical (part-of-speech and lemmas) levels. This study is part of a larger project, which includes other levels of analyses (syntax and discourse). The obtained results should help us rebut or identify new linguistic evidence participating in the manifes...

RÉSUMÉ. Les principaux travaux en fouille textuelle privilégient communément la taille du corpus sur sa qualité. Ainsi dans le cadre de l’alignement lexical à partir de corpus comparables, les meilleurs résultats sont obtenus pour des corpus de grande taille (plusieurs millions de mots). Pour les domaines de spécialité, et pour de nombreuses paires de langues, il n’est pas possible de disposer ...

RÉSUMÉ. Nous étudions, par des méthodes statistiques sur des corpus français et italiens, le phénomène de réduction des termes complexes dans les langues de spécialité. Il existe deux types de réductions : anaphorique et lexicale. Nous montrons que la réduction anaphorique dépend du type de discours (de vulgarisation, pédagogique, spécialisé) mais ne dépend ni du domaine, ni de la langue, alors...

This paper assesses the performance of three taggers (MBT, TnT and TreeTagger) when used for the morphosyntactic annotation of classical Latin texts. With this aim in view, we selected the training corpora, -as well as the samples used for tests-, from the texts of the LASLA database. The texts were chosen according to their ability to allow testing of the taggers sensitivity to stylistic, diac...

In the robust track of the 2008 CLEF evaluation campaign an enlarged English corpus was provided. For each term, the lemma, the part-of-speech (POS) and the Synset number extracted from WordNetTM (class number of the corresponding thesaurus) are given. Based on this corpus we tested several approaches to remove at least partially the underling lexical ambiguity. Using different IR models such a...

The interest in logical-semantic and semantic-information analysis of prognostic statements can be substantiated not only by the development of prognostics as such but also by the occurrence of prognostic statements in a number of empirical dissciplines where it has proved inevitable to operate with statements on the future states of the systems under investigation. Neither is it possible to ov...