Literatura académica sobre el tema "Représentations distributionnelles"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte las listas temáticas de artículos, libros, tesis, actas de conferencias y otras fuentes académicas sobre el tema "Représentations distributionnelles".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Artículos de revistas sobre el tema "Représentations distributionnelles"
Wauquier, Marine, Cécile Fabre y et Nabil Hathout. "Différenciation sémantique de dérivés morphologiques à l’aide de critères distributionnels". SHS Web of Conferences 46 (2018): 08006. http://dx.doi.org/10.1051/shsconf/20184608006.
Texto completoMelatagia Yonta, Paulin y Michael Franklin Mbouopda. "Named Entity Recognition in Low-resource Languages using Cross-lingual distributional word representation". Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées Volume 33 - 2020 - Special... (29 de septiembre de 2020). http://dx.doi.org/10.46298/arima.6439.
Texto completoTesis sobre el tema "Représentations distributionnelles"
Auguste, Jérémy. "Analyse du discours conversationnel dans le cadre de communications médiées par ordinateur". Electronic Thesis or Diss., Aix-Marseille, 2020. http://www.theses.fr/2020AIXM0228.
Texto completoDialogues are a central part of human society, and technological improvements only strengthen their use in more and more situations. Additional tools used to communicate from a distance allow the collection of large amounts of data, which can be used to produce various analyses and automatic systems.Conversational discourse analysis is a partial response to understand some aspects of language production in dialogues. It is used to characterize the different interactions between the messages of a dialogue, and thus highlight the different issues or identify the exchanges that are needed to solve the dialogue's main objectives.Discourse parsing is a challenging task. The high number of existing theories of discourse analysis shows that humans have a hard time defining discursive structures that model all possible interactions. This difficulty makes the production of annotated corpora expensive and the low amount of discursively annotated data makes the use of supervised learning algorithms impractical.In this thesis, I propose to produce representations of conversational discourse based on data that is partially annotated with discourse structures. The thesis is part of the DATCHA project which allowed me access to a large corpus of dialogues owned by the Orange company. This corpus allows us to explore different strategies in order to produce discourse representations: rely on an end-to-end model that predicts customer satisfaction; rely on dialogue acts to produce sentence embeddings; using supervised algorithms on an automatically enriched corpus
Venant, Fabienne. "Représentation et calcul dynamique du sens : exploration du lexique adjectival du français". Phd thesis, Ecole des Hautes Etudes en Sciences Sociales (EHESS), 2006. http://tel.archives-ouvertes.fr/tel-00067902.
Texto completoGrave, Edouard. "A Markovian approach to distributional semantics". Phd thesis, Université Pierre et Marie Curie - Paris VI, 2014. http://tel.archives-ouvertes.fr/tel-00940575.
Texto completoGrave, Edouard. "A Markovian approach to distributional semantics". Electronic Thesis or Diss., Paris 6, 2014. http://www.theses.fr/2014PA066002.
Texto completoThis thesis, which is organized in two independent parts, presents work on distributional semantics and on variable selection. In the first part, we introduce a new method for learning good word representations using large quantities of unlabeled sentences. The method is based on a probabilistic model of sentence, using a hidden Markov model and a syntactic dependency tree. The latent variables, which correspond to the nodes of the dependency tree, aim at capturing the meanings of the words. We develop an efficient algorithm to perform inference and learning in those models, based on online EM and approximate message passing. We then evaluate our models on intrinsic tasks such as predicting human similarity judgements or word categorization, and on two extrinsic tasks: named entity recognition and supersense tagging. In the second part, we introduce, in the context of linear models, a new penalty function to perform variable selection in the case of highly correlated predictors. This penalty, called the trace Lasso, uses the trace norm of the selected predictors, which is a convex surrogate of their rank, as the criterion of model complexity. The trace Lasso interpolates between the ℓ 1-norm and ℓ 2-norm. In particular, it is equal to the ℓ 1-norm if all predictors are orthogonal and to the ℓ 2-norm if all predictors are equal. We propose two algorithms to compute the solution of least-squares regression regularized by the trace Lasso, and perform experiments on synthetic datasets to illustrate the behavior of the trace Lasso
Capítulos de libros sobre el tema "Représentations distributionnelles"
Goron, Amina. "L’appropriation du français parlé au Tchad : une étude de cas de la valence verbale". En Multilinguisme, multiculturalisme et représentations identitaires, 15–31. Observatoire européen du plurilinguisme, 2021. http://dx.doi.org/10.3917/oep.goron.2021.01.0015.
Texto completo