@prefix dcat: . @prefix dct: . @prefix foaf: . @prefix vcard: . @prefix xsd: . a dcat:Dataset ; dct:description """ 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 revises each attachment in a parse by considering multiple alternative governors in the local syntactic neighborhood. We find that multiple-candidate approaches slightly improve parsing accuracy overall as well as for prepositional phrase attachment and coordination, two linguistic phenomena that exhibit high syntactic ambiguity. Our second research thread explores semi-supervised approaches for improving parsing accuracy and coverage. We test self-training within the journalistic domain as well as for adaptation to the medical domain, using a two-stage parsing approach based on that of McClosky et al. (2006). We then turn to lexical modeling over a large corpus: we model generalized lexical classes to reduce data sparseness, and prepositional phrase attachment preference to improve disambiguation. We find that semi-supervised approaches can sometimes improve parsing accuracy and coverage, without increasing time complexity. """ ; dct:identifier "tel-00860720" ; dct:issued "2026-05-09T19:03:43.185890"^^xsd:dateTime ; dct:language "en" ; dct:modified "2026-05-09T19:03:43.185895"^^xsd:dateTime ; dct:publisher ; dct:title "Efficient large-context dependency parsing and correction with distributional lexical resources" ; dcat:contactPoint [ a vcard:Organization ; vcard:fn "CCSD" ] ; dcat:distribution ; dcat:keyword "adaptation-de-domaine", "analyse-a-base-de-transitions", "analyse-syntaxique", "apprentissage-semi-supervise", "computational-linguistics", "dependency-grammar", "domain-adaptation", "grammaires-de-dependance", "infoeu-reposemanticsdoctoralthesis", "infoinfo-ttcomputer-science-csdocument-and-text-processing", "lexical-resources", "linguistique-informatique", "machines-a-vecteurs-supports", "ressources-lexicales", "semi-supervised-learning", "support-vector-machines", "syntactic-parsing", "theses", "transition-based-parsing" ; dcat:landingPage . a dcat:Distribution ; dct:format "HTML" ; dct:issued "2026-05-09T19:03:43.187743"^^xsd:dateTime ; dct:modified "2026-05-09T19:03:43.168262"^^xsd:dateTime ; dct:title "Efficient large-context dependency parsing and correction with distributional lexical resources" ; dcat:accessURL . a foaf:Agent ; foaf:name "test_moissonnage_selune" . a foaf:Document .