• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 174
  • 126
  • 14
  • Tagged with
  • 322
  • 187
  • 168
  • 146
  • 112
  • 79
  • 68
  • 68
  • 60
  • 48
  • 47
  • 40
  • 35
  • 35
  • 34
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
321

Neural approaches to dialog modeling

Sankar, Chinnadhurai 08 1900 (has links)
Cette thèse par article se compose de quatre articles qui contribuent au domaine de l’apprentissage profond, en particulier dans la compréhension et l’apprentissage des ap- proches neuronales des systèmes de dialogue. Le premier article fait un pas vers la compréhension si les architectures de dialogue neuronal couramment utilisées capturent efficacement les informations présentes dans l’historique des conversations. Grâce à une série d’expériences de perturbation sur des ensembles de données de dialogue populaires, nous constatons que les architectures de dialogue neuronal couramment utilisées comme les modèles seq2seq récurrents et basés sur des transformateurs sont rarement sensibles à la plupart des perturbations du contexte d’entrée telles que les énoncés manquants ou réorganisés, les mots mélangés, etc. Le deuxième article propose d’améliorer la qualité de génération de réponse dans les systèmes de dialogue de domaine ouvert en modélisant conjointement les énoncés avec les attributs de dialogue de chaque énoncé. Les attributs de dialogue d’un énoncé se réfèrent à des caractéristiques ou des aspects discrets associés à un énoncé comme les actes de dialogue, le sentiment, l’émotion, l’identité du locuteur, la personnalité du locuteur, etc. Le troisième article présente un moyen simple et économique de collecter des ensembles de données à grande échelle pour modéliser des systèmes de dialogue orientés tâche. Cette approche évite l’exigence d’un schéma d’annotation d’arguments complexes. La version initiale de l’ensemble de données comprend 13 215 dialogues basés sur des tâches comprenant six domaines et environ 8 000 entités nommées uniques, presque 8 fois plus que l’ensemble de données MultiWOZ populaire. / This thesis by article consists of four articles which contribute to the field of deep learning, specifically in understanding and learning neural approaches to dialog systems. The first article takes a step towards understanding if commonly used neural dialog architectures effectively capture the information present in the conversation history. Through a series of perturbation experiments on popular dialog datasets, wefindthatcommonly used neural dialog architectures like recurrent and transformer-based seq2seq models are rarely sensitive to most input context perturbations such as missing or reordering utterances, shuffling words, etc. The second article introduces a simple and cost-effective way to collect large scale datasets for modeling task-oriented dialog systems. This approach avoids the requirement of a com-plex argument annotation schema. The initial release of the dataset includes 13,215 task-based dialogs comprising six domains and around 8k unique named entities, almost 8 times more than the popular MultiWOZ dataset. The third article proposes to improve response generation quality in open domain dialog systems by jointly modeling the utterances with the dialog attributes of each utterance. Dialog attributes of an utterance refer to discrete features or aspects associated with an utterance like dialog-acts, sentiment, emotion, speaker identity, speaker personality, etc. The final article introduces an embedding-free method to compute word representations on-the-fly. This approach significantly reduces the memory footprint which facilitates de-ployment in on-device (memory constraints) devices. Apart from being independent of the vocabulary size, we find this approach to be inherently resilient to common misspellings.
322

Etude des dalles sur sols renforcés au moyen d'inclusions rigides ou non

Antoine, Pierre-Cornélius 21 December 2010 (has links)
Soft soil reinforcement by inclusion is a growing technique caracterized by a pile grid and a granular embankment introduced between the reinforced soil and the structure. Unlike traditionnal methods, the load is partially transferred to the pile heads by arching in the embankment. The application area of this research focuses on the shallow foundations case, in which the thickness of the embankment is small. The litterature review shows that only a few studies were dedicated to that case, and that fundamental questions remains concerning the load transfer in the embankment. Chosen method for this research consists in two-dimensionnal physical modelling, analysis of the conducted simulations, and development of an analytical model in order to predict the load transfer to the piles by arching in the embankment. The results of this PhD thesis provide original elements of evidence of the load transfer in the studied system, proposes an analytical model based on block division of the granular embankment by shear bands - which is in good agreement with experimental data - and lead to a better understanding of arching in soils. / Doctorat en Sciences de l'ingénieur / info:eu-repo/semantics/nonPublished

Page generated in 0.023 seconds