{"id":1701,"date":"2020-12-22T09:16:53","date_gmt":"2020-12-22T08:16:53","guid":{"rendered":"https:\/\/www.systransoft.com\/papers\/adipisci-in-et-qui\/"},"modified":"2023-11-16T18:20:29","modified_gmt":"2023-11-16T17:20:29","slug":"adipisci-in-et-qui","status":"publish","type":"paper","link":"https:\/\/www.systransoft.com\/fr\/ressources\/papers-and-publications\/adipisci-in-et-qui\/","title":{"rendered":"Int\u00e9gration de la terminologie de domaine dans la traduction automatique neuronale"},"content":{"rendered":"<span style=\"font-size: revert; color: initial;\">This paper extends existing work on terminology integration into Neural Machine Translation, a common industrial practice to dynamically adapt translation to a specific domain. Our method, based on the use of placeholders complemented with morphosyntactic annotation, efficiently taps into the ability of the neural network to deal with symbolic knowledge to surpass the surface generalization shown by alternative techniques. We compare our approach to state-of-the-art systems and benchmark them through a well-defined evaluation framework, focusing on actual application of terminology and not just on the overall performance. Results indicate the suitability of our method in the use-case where terminology is used in a system trained on generic data only..<\/span>","protected":false},"excerpt":{"rendered":"<p>Cet article \u00e9tend les travaux existants sur l'int\u00e9gration terminologique \u00e0 la traduction automatique neuronale, une pratique industrielle courante pour adapter dynamiquement la traduction \u00e0 un domaine sp\u00e9cifique. Notre m\u00e9thode, bas\u00e9e sur l'utilisation d'espaces r\u00e9serv\u00e9s compl\u00e9t\u00e9s par l'annotation morphosyntaxique, puise efficacement dans la capacit\u00e9 du r\u00e9seau neuronal \u00e0 g\u00e9rer les connaissances symboliques pour d\u00e9passer la g\u00e9n\u00e9ralisation de surface... <a href=\"https:\/\/www.systransoft.com\/fr\/ressources\/papers-and-publications\/adipisci-in-et-qui\/\">Suite<\/a><\/p>","protected":false},"featured_media":0,"template":"","class_list":["post-1701","paper","type-paper","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.systransoft.com\/fr\/wp-json\/wp\/v2\/paper\/1701","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.systransoft.com\/fr\/wp-json\/wp\/v2\/paper"}],"about":[{"href":"https:\/\/www.systransoft.com\/fr\/wp-json\/wp\/v2\/types\/paper"}],"wp:attachment":[{"href":"https:\/\/www.systransoft.com\/fr\/wp-json\/wp\/v2\/media?parent=1701"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}