Résumé-Abstract Cet article traite de l'annotation automatique d'informations temporelles dans des textes et vise plus particulièrement les relations entre événements introduits par les verbes dans chaque clause. Si ce problème... more
Résumé-Abstract Cet article traite de l'annotation automatique d'informations temporelles dans des textes et vise plus particulièrement les relations entre événements introduits par les verbes dans chaque clause. Si ce problème a mobilisé beaucoup de chercheurs sur le plan théorique, il reste en friche pour ce qui est de l'annotation automatique systématique (et son évaluation), même s' il existe des débuts de méthodologie pour faire réaliser la tâche par des humains. Nous proposons ici à la fois une méthode pour réaliser la tâche ...
Recent years have seen increasing attention in temporal processing of texts as well as a lot of standardization effort of temporal information in natural language. A central part of this information lies in the temporal relations between... more
Recent years have seen increasing attention in temporal processing of texts as well as a lot of standardization effort of temporal information in natural language. A central part of this information lies in the temporal relations between events described in a text, when their precise times or dates are not known. Reliable human annotation of such information is difficult, and automatic comparisons must follow procedures beyond mere precision-recall of local pieces of information, since a coherent picture can only be considered at a global ...
Research Interests:
Research Interests:
Research Interests:
ABSTRACT In this article, we present a novel graph-based approach for pseudo-relevance feedback. We model term co-occurences in a fixed window or at the document level as a graph and apply a random walk algorithm to select expansion... more
ABSTRACT In this article, we present a novel graph-based approach for pseudo-relevance feedback. We model term co-occurences in a fixed window or at the document level as a graph and apply a random walk algorithm to select expansion terms. Evaluation of the proposed approach on several standard TREC and CLEF collections including the recent TREC-Microblog dataset show that the proposed approach is competitive with state-of-the-art pseudo-relevance feedback models.
Je tiens à remercier les membres du jury de l'intérêt qu'ils ont manifesté pour mon travail. Je suis très reconnaissante à Maria Tereza Pazienza, Jean-Marie Pierrel et Bernard Victorri d'avoir accepté d'être... more
Je tiens à remercier les membres du jury de l'intérêt qu'ils ont manifesté pour mon travail. Je suis très reconnaissante à Maria Tereza Pazienza, Jean-Marie Pierrel et Bernard Victorri d'avoir accepté d'être rapporteurs. Leurs remarques ainsi que celles de Benoît Habert sont ...
Research Interests:
Research Interests: Dialogue()
()
Research Interests:
... Vries CWI Paul Ogilvie Carnegie Mellon University Benjamin Piwowarski Universidad de Chile Relevance Feedback Task Yosi Mass IBM ... University of Duisburg-Essen Document Mining Track Ludovic Denoyer Laboratoire... more
... Vries CWI Paul Ogilvie Carnegie Mellon University Benjamin Piwowarski Universidad de Chile Relevance Feedback Task Yosi Mass IBM ... University of Duisburg-Essen Document Mining Track Ludovic Denoyer Laboratoire d'Informatique de Paris 6 Patrick Gallinari Laboratoire ...
... com Xavier Tannier Ecole Nationale Supérieure des Mines 158 Cours Fauriel 42023 Saint-Etienne, France tannier@ emse. ... Indeed, many approaches to XML-IR rely on database tech-nology as a back-end system, rather than rely on IR... more
... com Xavier Tannier Ecole Nationale Supérieure des Mines 158 Cours Fauriel 42023 Saint-Etienne, France tannier@ emse. ... Indeed, many approaches to XML-IR rely on database tech-nology as a back-end system, rather than rely on IR spe-cific file structures. ...
The Quaero project organized a set of evaluations of Named Entity recognition systems in 2009, including reference extraction in patent text. The LIMSI participated in this evaluation. The task and its metrics is presented, followed by a... more
The Quaero project organized a set of evaluations of Named Entity recognition systems in 2009, including reference extraction in patent text. The LIMSI participated in this evaluation. The task and its metrics is presented, followed by a complete system description and the ...
Research Interests:
... afin de déterminer la catégorie morphosyntaxique des mots de la question, pour choisir les mots « importants » et procéder à l'interrogation via un ... n'est pas le cas dans le cadre d'une requête au sens de la... more
... afin de déterminer la catégorie morphosyntaxique des mots de la question, pour choisir les mots « importants » et procéder à l'interrogation via un ... n'est pas le cas dans le cadre d'une requête au sens de la recherche d'information : dans un moteur de recherche classique, la ...
The panel will take as its starting point the central stated goal of computational linguistics:" to create a machine that can meaningfully communicate with people (subsuming the capabilities for translation, question answering,... more
The panel will take as its starting point the central stated goal of computational linguistics:" to create a machine that can meaningfully communicate with people (subsuming the capabilities for translation, question answering, information extraction, text summarization and reasoning)", and it will aim at identifying the grand challenges that we see ahead of us that would-advance our knowledge and capabilities-provide the world with better communication facilities-unite the players in the field.