{"id":1702,"date":"2022-06-11T10:17:59","date_gmt":"2022-06-11T08:17:59","guid":{"rendered":"https:\/\/www-staging.systransoft.com\/papers\/et-ut-non-rerum-nobis\/"},"modified":"2023-11-16T18:21:30","modified_gmt":"2023-11-16T17:21:30","slug":"et-ut-non-rerum-nobis","status":"publish","type":"paper","link":"https:\/\/www-staging.systransoft.com\/fr\/ressources\/papers-and-publications\/et-ut-non-rerum-nobis\/","title":{"rendered":"Adaptation multidomaine dans la traduction automatique neuronale avec des strat\u00e9gies d'\u00e9chantillonnage dynamique"},"content":{"rendered":"Building effective Neural Machine Translation models often implies accommodating diverse sets of heterogeneous data so as to optimize performance for the domain(s) of interest. Such multi-source \/ multi-domain adaptation problems are typically approached through instance selection or reweighting strategies, based on a static assessment of the relevance of training instances with respect to the task at hand. In this paper, we study dynamic data selection strategies that are able to automatically re-evaluate the usefulness of data samples and to evolve a data selection policy in the course of training. Based on the results of multiple experiments, we show that such methods constitute a generic framework to automatically and effectively handle a variety of real-world situations, from multi-source domain adaptation to multi-domain learning and unsupervised domain adaptation.","protected":false},"excerpt":{"rendered":"<p>Construire des mod\u00e8les efficaces de traduction automatique neuronale implique souvent de prendre en compte divers ensembles de donn\u00e9es h\u00e9t\u00e9rog\u00e8nes afin d'optimiser les performances pour le(s) domaine(s) d'int\u00e9r\u00eat. Ces probl\u00e8mes d'adaptation multisources\/multidomaines sont g\u00e9n\u00e9ralement abord\u00e9s par le biais de strat\u00e9gies de s\u00e9lection ou de repond\u00e9ration des instances, sur la base d'une \u00e9valuation statique de la pertinence des instances de formation par rapport \u00e0 la t\u00e2che ... <a href=\"https:\/\/www-staging.systransoft.com\/fr\/ressources\/papers-and-publications\/et-ut-non-rerum-nobis\/\">Suite<\/a><\/p>","protected":false},"featured_media":0,"template":"","class_list":["post-1702","paper","type-paper","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www-staging.systransoft.com\/fr\/wp-json\/wp\/v2\/paper\/1702","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www-staging.systransoft.com\/fr\/wp-json\/wp\/v2\/paper"}],"about":[{"href":"https:\/\/www-staging.systransoft.com\/fr\/wp-json\/wp\/v2\/types\/paper"}],"wp:attachment":[{"href":"https:\/\/www-staging.systransoft.com\/fr\/wp-json\/wp\/v2\/media?parent=1702"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}