{"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\/es\/recursos\/papers-and-publications\/alias-et-quia-sint-velit-sit\/","title":{"rendered":"Deserci\u00f3n de grupo latente para traducci\u00f3n autom\u00e1tica multiling\u00fce y multidominio"},"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 traducci\u00f3n autom\u00e1tica multidominio y multiling\u00fce a menudo se basa en estrategias de uso compartido de par\u00e1metros, donde grandes porciones de la red est\u00e1n destinadas a capturar las caracter\u00edsticas comunes de las tareas en cuesti\u00f3n, mientras que partes m\u00e1s peque\u00f1as se reservan para modelar las peculiaridades de un idioma o un dominio. En los enfoques basados en adaptadores, estas estrategias est\u00e1n codificadas en la arquitectura de red, independiente ... <a href=\"https:\/\/www-staging.systransoft.com\/es\/recursos\/papers-and-publications\/alias-et-quia-sint-velit-sit\/\">Continuaci\u00f3n<\/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\/es\/wp-json\/wp\/v2\/paper\/1698","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www-staging.systransoft.com\/es\/wp-json\/wp\/v2\/paper"}],"about":[{"href":"https:\/\/www-staging.systransoft.com\/es\/wp-json\/wp\/v2\/types\/paper"}],"wp:attachment":[{"href":"https:\/\/www-staging.systransoft.com\/es\/wp-json\/wp\/v2\/media?parent=1698"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}