This paper describes SYSTRAN’s systems submitted to the WMT 2017 shared news translation task for English-German, in both translation directions. Our systems are built using OpenNMT1, an opensource neural machine translation system, implementing sequence-to-sequence models with LSTM encoder\/decoders and attention. We experimented using monolingual data automatically back-translated. Our resulting models are further hyperspecialised with an adaptation technique that finely tunes models according to the evaluation test sentences.<\/p>","protected":false},"excerpt":{"rendered":"
This paper describes SYSTRAN’s systems submitted to the WMT 2017 shared news translation task for English-German, in both translation directions. Our systems are built using OpenNMT1, an opensource neural machine translation system, implementing sequence-to-sequence models with LSTM encoder\/decoders and attention. We experimented using monolingual data automatically back-translated. Our resulting models are further hyperspecialised with an … Suite<\/a><\/p>","protected":false},"featured_media":0,"template":"","class_list":["post-3296","paper","type-paper","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www-staging.systransoft.com\/fr\/wp-json\/wp\/v2\/paper\/3296","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=3296"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}