{"id":1698,"date":"2022-07-01T17:46:52","date_gmt":"2022-07-01T15:46:52","guid":{"rendered":"https:\/\/www-staging.systransoft.com\/papers\/alias-et-quia-sint-velit-sit\/"},"modified":"2023-11-16T18:21:44","modified_gmt":"2023-11-16T17:21:44","slug":"alias-et-quia-sint-velit-sit","status":"publish","type":"paper","link":"https:\/\/www-staging.systransoft.com\/fr\/ressources\/papers-and-publications\/alias-et-quia-sint-velit-sit\/","title":{"rendered":"Abandon de groupe latent pour la traduction automatique multilingue et multidomaine"},"content":{"rendered":"<p><em>Multidomain and multilingual machine translation often rely on parameter sharing strategies, where large portions of the network are meant to capture the commonalities of the tasks at hand, while smaller parts are reserved to model the peculiarities of a language or a domain. In adapter-based approaches, these strategies are hardcoded in the network architecture, independent of the similarities between tasks. In this work, we propose a new method to better take advantage of these similarities, using a latent-variable model. We also develop new techniques to train this model end-to-end and report experimental results showing that the learned patterns are both meaningful and yield improved translation performance without any increase of the model size.<\/em><\/p>","protected":false},"excerpt":{"rendered":"<p>La traduction automatique multidomaine et multilingue repose souvent sur des strat\u00e9gies de partage de param\u00e8tres, o\u00f9 de grandes parties du r\u00e9seau sont destin\u00e9es \u00e0 capturer les points communs des t\u00e2ches \u00e0 accomplir, tandis que des parties plus petites sont r\u00e9serv\u00e9es pour mod\u00e9liser les particularit\u00e9s d'une langue ou d'un domaine. Dans les approches bas\u00e9es sur la carte, ces strat\u00e9gies sont cod\u00e9es en dur dans l'architecture r\u00e9seau, ind\u00e9pendantes... <a href=\"https:\/\/www-staging.systransoft.com\/fr\/ressources\/papers-and-publications\/alias-et-quia-sint-velit-sit\/\">Suite<\/a><\/p>","protected":false},"featured_media":0,"template":"","class_list":["post-1698","paper","type-paper","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www-staging.systransoft.com\/fr\/wp-json\/wp\/v2\/paper\/1698","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=1698"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}