This thesis explores ways to improve the accuracy and coverage of efficient statistical dependency parsing. We employ transition-based parsing with models learned using Support Vector Machines (Cortes and Vapnik, 1995), and our experiments are carried out on French. Transition-based parsing is very fast due to the computational efficiency of its underlying algorithms, which are based on a local optimization of attachment decisions. Our first research thread is thus to increase the syntactic context used. From the arc-eager transition system (Nivre, 2008) we propose a variant that simultaneously considers multiple candidate governors for right-directed attachments. We also test parse correction, inspired by Hall and Novák (2005), which revi...
Dans cette thèse, nous explorons l'analyse syntaxique robuste statistique du français. Notre princip...
Cette thèse porte sur l'intégration de ressources lexicales et syntaxiques du français dans deux tâc...
The present work investigates the role of two types of distributional models in resolving the prepos...
This thesis explores ways to improve the accuracy and coverage of efficient statistical dependency p...
Cette thèse présente des méthodes pour améliorer l'analyse syntaxique probabiliste en dépendances. N...
Analyse probabiliste est l'un des domaines de recherche les plus attractives en langage naturel En t...
In this thesis we explore robust statistical syntax analysis for French. Our main concern is to expl...
International audienceThis paper investigates the impact on French dependency parsing of lexical gen...
International audienceTransition-based dependency parsing often uses deterministic techniques, where...
International audienceTreebanks are not large enough to reliably model precise lexical phenomena. Th...
9 pagesInternational audienceWe compare the performance of three statistical parsing architectures o...
This thesis takes place in the domain of syntactic dependency parsing. On the one hand we study the ...
International audienceThis paper develops a framework for syntactic dependency parse correction. Dep...
This thesis focuses on the integration of lexical and syntactic resources of French in two fundament...
Dans cette thèse, nous explorons l'analyse syntaxique robuste statistique du français. Notre princip...
Cette thèse porte sur l'intégration de ressources lexicales et syntaxiques du français dans deux tâc...
The present work investigates the role of two types of distributional models in resolving the prepos...
This thesis explores ways to improve the accuracy and coverage of efficient statistical dependency p...
Cette thèse présente des méthodes pour améliorer l'analyse syntaxique probabiliste en dépendances. N...
Analyse probabiliste est l'un des domaines de recherche les plus attractives en langage naturel En t...
In this thesis we explore robust statistical syntax analysis for French. Our main concern is to expl...
International audienceThis paper investigates the impact on French dependency parsing of lexical gen...
International audienceTransition-based dependency parsing often uses deterministic techniques, where...
International audienceTreebanks are not large enough to reliably model precise lexical phenomena. Th...
9 pagesInternational audienceWe compare the performance of three statistical parsing architectures o...
This thesis takes place in the domain of syntactic dependency parsing. On the one hand we study the ...
International audienceThis paper develops a framework for syntactic dependency parse correction. Dep...
This thesis focuses on the integration of lexical and syntactic resources of French in two fundament...
Dans cette thèse, nous explorons l'analyse syntaxique robuste statistique du français. Notre princip...
Cette thèse porte sur l'intégration de ressources lexicales et syntaxiques du français dans deux tâc...
The present work investigates the role of two types of distributional models in resolving the prepos...