Dissertations / Theses on the topic 'Apprentissage contrastif'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 17 dissertations / theses for your research on the topic 'Apprentissage contrastif.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Bakkali, Souhail. "Multimodal Document Understanding with Unified Vision and Language Cross-Modal Learning." Electronic Thesis or Diss., La Rochelle, 2022. http://www.theses.fr/2022LAROS046.
Full textThe frameworks developed in this thesis were the outcome of an iterative process of analysis and synthesis between existing theories and our performed studies. More specifically, we wish to study cross-modality learning for contextualized comprehension on document components across language and vision. The main idea is to leverage multimodal information from document images into a common semantic space. This thesis focuses on advancing the research on cross-modality learning and makes contributions on four fronts: (i) to proposing a cross-modal approach with deep networks to jointly leverage visual and textual information into a common semantic representation space to automatically perform and make predictions about multimodal documents (i.e., the subject matter they are about); (ii) to investigating competitive strategies to address the tasks of cross-modal document classification, content-based retrieval and few-shot document classification; (iii) to addressing data-related issues like learning when data is not annotated, by proposing a network that learns generic representations from a collection of unlabeled documents; and (iv) to exploiting few-shot learning settings when data contains only few examples
Do, Quoc khanh. "Apprentissage discriminant des modèles continus en traduction automatique." Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLS071/document.
Full textOver the past few years, neural network (NN) architectures have been successfully applied to many Natural Language Processing (NLP) applications, such as Automatic Speech Recognition (ASR) and Statistical Machine Translation (SMT).For the language modeling task, these models consider linguistic units (i.e words and phrases) through their projections into a continuous (multi-dimensional) space, and the estimated distribution is a function of these projections. Also qualified continuous-space models (CSMs), their peculiarity hence lies in this exploitation of a continuous representation that can be seen as an attempt to address the sparsity issue of the conventional discrete models. In the context of SMT, these echniques have been applied on neural network-based language models (NNLMs) included in SMT systems, and oncontinuous-space translation models (CSTMs). These models have led to significant and consistent gains in the SMT performance, but are also considered as very expensive in training and inference, especially for systems involving large vocabularies. To overcome this issue, Structured Output Layer (SOUL) and Noise Contrastive Estimation (NCE) have been proposed; the former modifies the standard structure on vocabulary words, while the latter approximates the maximum-likelihood estimation (MLE) by a sampling method. All these approaches share the same estimation criterion which is the MLE ; however using this procedure results in an inconsistency between theobjective function defined for parameter stimation and the way models are used in the SMT application. The work presented in this dissertation aims to design new performance-oriented and global training procedures for CSMs to overcome these issues. The main contributions lie in the investigation and evaluation of efficient training methods for (large-vocabulary) CSMs which aim~:(a) to reduce the total training cost, and (b) to improve the efficiency of these models when used within the SMT application. On the one hand, the training and inference cost can be reduced (using the SOUL structure or the NCE algorithm), or by reducing the number of iterations via a faster convergence. This thesis provides an empirical analysis of these solutions on different large-scale SMT tasks. On the other hand, we propose a discriminative training framework which optimizes the performance of the whole system containing the CSM as a component model. The experimental results show that this framework is efficient to both train and adapt CSM within SMT systems, opening promising research perspectives
Contreras, Roa Leonardo. "Prosodie et apprentissage des langues : étude contrastive de l’interlangue d’apprenants d’anglais francophones et hispanophones." Thesis, Rennes 2, 2019. http://www.theses.fr/2019REN20053.
Full textThis thesis is a study of the prosodic interlanguage of students of English as a foreign language whose native language is French or Spanish. It is organized in two main parts. The first part is a study of the methods of conception and representation of prosody for the analysis of interlanguage – a hybrid linguistic system which includes characteristics of the student's native language, characteristics of the target language, and intermediate developmental or characteristics. This provides a methodological framework for the phonetic analysis and phonological interpretation of this type of prosodic systems. The second part is the implementation of this methodology through a contrastive interlanguage analysis conducted through the study of an oral corpus of students of English as a foreign language. The results show traces of the influence of their respective native languages at the phonetic and phonological levels, as well as developmental characteristics common to both groups of learners. The results serve as a basis for reflection on the levels of abstraction in the study of prosody and on the didactic priorities for teaching oral English at a university level
Poezevara, Guillaume. "Fouille de graphes pour la découverte de contrastes entre classes : application à l'estimation de la toxicité des molécules." Phd thesis, Université de Caen, 2011. http://tel.archives-ouvertes.fr/tel-01018425.
Full textZhang, Yarui. "Non-linear electromagnetic imaging : from sparsity-preserving wavelet-based algorithms to deep learning." Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPAST167.
Full textThis work deals with nonlinear ill-posed electromagnetic imaging from time-harmonic data within a two-dimensional scattering experiment, the focus being on two approaches in the framework of the contrast-source inversion (CSI). The first approach is a group sparsity penalized CSI in the wavelet domain, the second is an unrolled deep learning scheme. In the first approach, dependency exists between wavelet coefficients at different scales, referred to as parent-child relationship, which yields a wavelet quadtree structure so that wavelet coefficients are both pixel-wise and group-wise sparse. Emphasis is on the dual-tree complex wavelet transform (CWT) to achieve this result. A '2;1 norm added to the standard cost function is to enforce group sparsity onto the wavelet coefficients of the spatially-varying contrast. The replication strategy is combined with the proximal method to solve the overlapping group penalized problem. The second approach is inspired by the unrolled method. By embedding the CSI iterations into the deep learning model, the domain knowledge is incorporated into the learning process. In both cases, thorough numerical tests are carried out to evaluate performance, stability, robustness, and reliability with comparisons with more standard solutions (like CSI, discrete wavelet transform (DWT) and U-net), which exhibit the advantage of the proposed approaches under many aspects
Patrukhina, Liubov. "À la recherche des particules modales dans les cours pour débutants ˸ étude expérimentale dans le cadre de l’enseignement-apprentissage de l’allemand langue étrangère en France et en Russie." Thesis, Paris 3, 2019. http://www.theses.fr/2019PA030037.
Full textThe research presented in this dissertation analyzes the acquisition of German modal particles by beginner-level learners. This project seeks firstly to ascertain if introducing the particles early and explicitly into the German-as-a-foreign-language can help learners to understand and use them more effectively. Secondly, it attempts to determine whether learners’ mother tongue influences the acquisition process of German modal particles. The first chapter sets the conceptual background, retracing the concepts in linguistics and language didactics that are fundamental to this study: Contrastive Linguistics, Corpus Linguistics, and Speech Acts Theory, as well as Foreign Language Teaching Methods and Approaches. It also presents the corpus of young peoples’ spoken German collected specifically for the didactic purposes of this dissertation. The second chapter analyzes the different methods of teaching modal particles put forward in textbooks and grammar books, as well as in dictionaries and exercise books devoted to the subject. Following this review, I propose my own approach based on two innovative teaching tools: recordings from my corpus of spoken German, and bilingual tables with comments in German, French or Russian on how German modal particles function. The third chapter describes the implementation of my method by presenting the results from an experiment of teaching German-as-a-foreign-language to French-, Russian- and Chinese-speaking learners. The thesis ends with methodological recommendations for teaching German modal particles
Die vorliegende Dissertation hat zum Ziel, den Erwerb der Modalpartikeln durch DaF-Lernende auf Anfängerniveau zu untersuchen. Allem voran wird der Frage nachgegangen, ob und wenn ja wie, eine explizite und frühe Behandlung der Modalpartikeln im DaF-Unterricht deren Produktion und Verständnis fördern kann. Anschließend wird der Versuch unternommen, einen möglichen positiven Einfluss der Muttersprache auf den Erwerb deutscher Modalpartikeln herauszufinden. Das erste Kapitel setzt den theoretischen Rahmen der Dissertation, indem es linguistische und sprachdidaktische Konzepte darlegt, die grundlegend für diese Arbeit sind: kontrastive Linguistik, Korpuslinguistik, Sprechakttheorie und Methoden des Fremdsprachenunterrichts. Es wird außerdem das Korpus “Gesprochenes Deutsch junger Muttersprachler“ beschrieben, das gezielt für die didaktischen Zwecke der Dissertation zusammengestellt worden ist. Im zweiten Kapitel werden Ansätze und Methoden zur Einführung der Modalpartikeln durchleuchtet, die in modernen DaF-Lehrwerken und Grammatiken sowie in thematischen Lexika und Übungsbüchern eingesetzt werden. Im Anschluss wird die eigene Herangehensweise dargestellt, die auf zwei innovativen Lehrmaterialien fußt: Didaktisierte Audioaufnahmen aus dem Korpus und zweisprachige Tabellen, die auf Deutsch, Französisch oder Russisch den Gebrauch der Modalpartikeln erläutern. Im dritten Kapitel wird die Umsetzung dieses Ansatzes beschrieben, der im Rahmen eines experimentellen DaF-Unterrichts mit russisch-, französisch- und chinesischsprachigen Deutschlernenden auf die Probe gestellt wurde. Abschließend werden methodische Vorschläge zur Behandlung der Modalpartikeln im DaF-Unterricht gemacht
Contemori, Giulio. "Amélioration de la fonctionnalité visuelle par l'utilisation concomitante de l'apprentissage perceptif et de la stimulation cérébrale : le cas de la dégénérescence maculaire." Thesis, Toulouse 3, 2020. http://www.theses.fr/2020TOU30054.
Full textMacular degeneration (MD) is a common visual disorder in the aging population characterized by a loss of central vision, reduced visual acuity contrast sensitivity, and increased crowding. This impairment strongly affects the quality of life and personal autonomy. There is currently no cure for AMD, available treatment options are only able to slow down the disease, and even palliative treatments are rare. After the emergence of the central scotoma, patients with MD develop one or more eccentric fixation areas - preferred retinal loci (PRLs) - that are used for fixation, reading, tracking, and other visual tasks that require finer ocular abilities. The final goal of the project was to investigate and to improve the residual visual abilities in the PRL. Four studies were conducted in total. Study 1 was conducted in MD patients to investigate whether after the emergence of the scotoma, the PRL acquire enhanced abilities in the processing of the visual information through spontaneous or use-dependent adaptive plasticity. Study 2 aimed to assess the effects of a single administration of transcranial random noise electrical stimulation (tRNS), a subtype of non-invasive transcranial electrical stimulation, on the spatial integration in the healthy visual cortex. Study 3 aimed to assess the between session effect of daily repeated tRNS coupled with perceptual training. The objective of study 4 was to translate the previous findings into a clinically applicable treatment approach by combining tRNS and perceptual training in adult patients with MD. Contrary to previous results, we found neither a phenomenon of spontaneous nor use-dependent cortical plasticity undergoing in the PRL before the training. We also found that the tRNS was able to modulate the visuospatial integration in the early visual processing, promoting plastic changes in the stimulated network. Its effects were not limited to the short-term modulation but also produced a boosting of the learning in a crowding task. The final experiment showed that a combination of tRNS and perceptual training could result in greater improvements and larger transfer to untrained visual tasks in adults with MD than training alone. Overall, our results indicate that tRNS of the visual cortex has potential application as an additional therapy to improve vision in adults with bilateral central blindness
Vanhille, Mohini. "Cultures de collaboration dans une activité de conception créative : une approche contrastée, développementale et dialogique des interactions dans des équipes d'élèves-ingénieurs français et japonais." Thesis, Paris, ENST, 2017. http://www.theses.fr/2017ENST0010/document.
Full textOn the basis of the concept of “cultures of collaboration”, this thesis offers a situated perspective, i.e anchored in a given situation, within the framework of CSCW and CSCL research, on the study of collaboration and the evaluation of it quality. In order to question collaborative practices and their associated values, two case studies have been carried. Following an intercultural approach, the first study compares social representations of collaboration, “ideal” and situated, of engineering-students of Telecom ParisTech in France and TokyoTech in Japan. According to a developmental and dialogic approach, the second study analyses the development and the quality of cultures of collaboration in interactions of two groups of Telecom ParisTech engineering-students taking part in the PACT course, whose aim is to encourage collaborative learning in creative engineering design activities. A multi-dimensional assessment method of the quality of collaboration (“Q.C2”), based on a previous version (“Q.C”), has been developed within the framework of the analysis of these two studies. Empirical contributions of this work allow the identification of the influence of cultural context, of temporality and of the quality of affective dimensions of activity on the development, the nature and the objectives of collaboration, understood in terms of the concept of cultures of collaboration
Lu, Yan. "Etude contrastive de la prosodie audio-visuelle des affects sociaux en chinois mandarin vs.français : vers une application pour l'apprentissage de la langue étrangère ou seconde." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GREAL001/document.
Full textIn human face-to-face interaction, social affects should be distinguished from emotional expressions, triggered by innate and involuntary controls of the speaker, by their nature of voluntary controls expressed within the audiovisual prosody and by their important role in the realization of speech acts. They also put into circulation between the interlocutors the social context and social relationship information. The prosody is a main vector of social affects and its cross-language variability is a challenge for language description as well as for foreign language teaching. Thus, cultural and linguistic specificities of the socio-affective prosody in oral communication could be a difficulty, even a risk of misunderstanding, for foreign language and second language learners. This thesis is dedicated to intra- and intercultural studies on perception of the prosody of 19 social affects in Mandarin Chinese and in French, on their cognitive representations, as well as on Chinese and French socio-affective prosody learning for foreign and second language learners. The first task of this thesis concerns the construction of a large audio-visual corpus of Chinese social affects. 152 sentences with the variation of length, tone location and syntactic structures of utterances, have been incorporated with 19 social affects. This corpus is served to examine the identification and perceptual confusion of these Chinese social affects by native and non-native listeners, as well as the tonal effect on non-native subjects' identification. Experimental results reveal that the majority of social affects are similarly perceived by native and non-native subjects, otherwise, some differences are also observed. Lexical tones lead to certain perceptual problems also for Vietnamese listeners (of a tonal language) and for French listeners (of a non-tonal language). In parallel, an acoustic analysis investigates the production side of prosodic socio-affects in Mandarin Chinese, and allows highlighting the more prominent patterns of acoustical variations as well as supporting the perceptual resultants obtained on the same expressions. Then, a study on conceptual and psycho-acoustic distances between social affects is carried out with Chinese and French subjects. The main results indicate that all subjects share to a very large extent the knowledge about these 19 social affects, regardless of their mother language, gender or how to present social affects (concept or acoustic realization). Finally, the last chapter of thesis is dedicated to the differences in the perception of 11 Chinese social affects expressed in different modalities (audio only, video only and audio-visual) for French learners and native subjects, as well as in the perception of the same French socio-affects for Chinese learners and native subjects. According to the results, the identification of affective expressions depends more on their affective values and on their presentation modality. Subject's learning level (beginner or intermediate) does not have a significant effect on their identification
Appetito, Paola. "Étude contrastive du langage publicitaire en français et en italien : approche linguistique et perspectives didactiques pour l’enseignement du français en Italie et de l’italien en France." Thesis, Aix-Marseille, 2016. http://www.theses.fr/2016AIXM3034.
Full textThe purpose of this research work is to develop a renewed pedagogical approach which uses advertising as tool for the teaching of French and Italian as foreign languages. To this end, we have made reference to the major studies in this area, and we have analysed the characteristics of advertising adopting a contrastive approach in French and Italian and in a didactic perspective. The study of the evolution of the strategies and forms of encoding of the advertisements message – as well as the linguistic, iconographic and cultural peculiarities – is put at the service of an approach which places itself in an action-orientated, intercultural and plurilinguistic dimension. This approach – adopted in the educational plans of French and Italian schools and universities - meets both the recommendations of the CEFR and the media literacy endorsed by the EU. In addition to illustrate the advantages of a didactic exploitation of this type of documents at different levels of competence and for different users, our objective is also to prove the effectiveness of certain methodological approaches, especially those integrating new information and communication technologies and digital tools.This research work represents the general framework of an extended multimedia, intercultural and interlinguistic programme for the teaching of Italian and French and it will lead to the creation of a website or an educational blog, offering the opportunity to implement and catalogue new pedagogical scenarios in the field of teaching-learning of foreign languages in schools and universities
Prevost, Raphaël. "Méthodes variationnelles pour la segmentation d'images à partir de modèles : applications en imagerie médicale." Phd thesis, Université Paris Dauphine - Paris IX, 2013. http://tel.archives-ouvertes.fr/tel-00932995.
Full textApidianaki, Marianna. "Acquisition automatique de sens pour la désambiguïsation et la sélection lexicale en traduction." Phd thesis, Université Paris-Diderot - Paris VII, 2008. http://tel.archives-ouvertes.fr/tel-00322285.
Full textNous proposons une méthode d'acquisition de sens permettant d'établir des correspondances sémantiques de granularité variable entre les mots de deux langues en relation de traduction. L'induction de sens est effectuée par une combinaison d'informations distributionnelles et traductionnelles extraites d'un corpus bilingue parallèle. La méthode proposée étant à la fois non supervisée et entièrement fondée sur des données, elle est, par conséquent, indépendante de la langue et permet l'élaboration d'inventaires sémantiques relatifs aux domaines représentés dans les corpus traités.
Les résultats de cette méthode sont exploités par une méthode de désambiguïsation lexicale, qui attribue un sens à de nouvelles instances de mots ambigus en contexte, et par une méthode de sélection lexicale, qui propose leur traduction la plus adéquate. On propose finalement une évaluation pondérée des résultats de désambiguïsation et de sélection lexicale, en nous fondant sur l'inventaire construit par la méthode d'acquisition de sens.
Farkamekh, Leila. "Les influences de l'apprentissage de la première langue étrangère (anglais) sur l'apprentissage de la deuxième langue étrangère (français) chez les apprenants persanophones." Phd thesis, Bordeaux 3, 2006. http://www.theses.fr/2006BOR30049.
Full textIn the Iranian educational system, the English language is taught as the first foreign language, and the study of French usually takes place after the study of English. We study the influences of the previous knowledge of English on the learning of the French language by Persian speakers. We made the hypothesis, based both on our experience as a student and as a teacher, that the students will refer to their previous knowledge of English (L2) for learning French in the position of the third language, because these two languages are typologically close, which is not the case of Persian and French. Focussing on gender, number and on some aspects of word order, we identified. The errors in a corpus that was collected in two Iranian universities, and we interpreted them in the light of contrastive analysis of the three languages, Persian (L1), English (L2) and French (L3). Six parts of speech (article, possessive adjective, demonstrative adjective, qualificative adjective, direct/indirect object pronoun, past participle) are considered, as well as interrogative and négative forms. This morpho-syntactic study provided us with results which reveal the predominance of certain types of errors. The concepts of bridging language and empty notions are summoned to account for the presence of cross-linguistic influences
Delalleau, Olivier. "Apprentissage machine efficace : théorie et pratique." Thèse, 2012. http://hdl.handle.net/1866/8669.
Full textDespite constant progress in terms of available computational power, memory and amount of data, machine learning algorithms need to be efficient in how they use them. Although minimizing cost is an obvious major concern, another motivation is to attempt to design algorithms that can learn as efficiently as intelligent species. This thesis tackles the problem of efficient learning through various papers dealing with a wide range of machine learning algorithms: this topic is seen both from the point of view of computational efficiency (processing power and memory required by the algorithms) and of statistical efficiency (n umber of samples necessary to solve a given learning task).The first contribution of this thesis is in shedding light on various statistical inefficiencies in existing algorithms. Indeed, we show that decision trees do not generalize well on tasks with some particular properties (chapter 3), and that a similar flaw affects typical graph-based semi-supervised learning algorithms (chapter 5). This flaw is a form of curse of dimensionality that is specific to each of these algorithms. For a subclass of neural networks, called sum-product networks, we prove that using networks with a single hidden layer can be exponentially less efficient than when using deep networks (chapter 4). Our analyses help better understand some inherent flaws found in these algorithms, and steer research towards approaches that may potentially overcome them. We also exhibit computational inefficiencies in popular graph-based semi-supervised learning algorithms (chapter 5) as well as in the learning of mixtures of Gaussians with missing data (chapter 6). In both cases we propose new algorithms that make it possible to scale to much larger datasets. The last two chapters also deal with computational efficiency, but in different ways. Chapter 7 presents a new view on the contrastive divergence algorithm (which has been used for efficient training of restricted Boltzmann machines). It provides additional insight on the reasons why this algorithm has been so successful. Finally, in chapter 8 we describe an application of machine learning to video games, where computational efficiency is tied to software and hardware engineering constraints which, although often ignored in research papers, are ubiquitous in practice.
Thomas-Anugraham, Alice. "Apprentissage du français comme langue étrangère (L3+) par des étudiants indiens." Thèse, 2008. http://hdl.handle.net/1866/6422.
Full textNguyen, Van Nhan. "Pronoms personnels du français et du vietnamien : étude contrastive et analyse des erreurs en FLE." Thèse, 2004. http://hdl.handle.net/1866/16565.
Full textJohnson, Kevin. "L'orientation vers les buts : le contraste de deux modèles." Thèse, 2008. http://hdl.handle.net/1866/7437.
Full text