{"id":1697,"date":"2020-07-02T10:08:48","date_gmt":"2020-07-02T08:08:48","guid":{"rendered":"https:\/\/www-staging.systransoft.com\/papers\/porro-in-qui-porro-ullam-adipisci-rem\/"},"modified":"2023-11-16T18:18:47","modified_gmt":"2023-11-16T17:18:47","slug":"porro-in-qui-porro-ullam-adipisci-rem","status":"publish","type":"paper","link":"https:\/\/www-staging.systransoft.com\/es\/recursos\/papers-and-publications\/porro-in-qui-porro-ullam-adipisci-rem\/","title":{"rendered":"Boosting Neural Machine Translation with Similar Translations"},"content":{"rendered":"This presentation demonstrates data augmentation methods for Neural Machine Translation to make use of similar translations, in a comparable way a human translator employs fuzzy matches. We show how we simply feed the neural model with information on both source and target sides of the fuzzy matches, and we also extend the similarity to include semantically related translations retrieved using distributed sentence representations. We show that translations based on fuzzy matching provide the model with \u00ab copy \u00bb information while translations based on embedding similarities tend to extend the translation \u00ab context \u00bb. Results indicate that the effect from both similar sentences are adding up to further boost accuracy, are combining naturally with model fine-tuning and are providing dynamic adaptation for unseen translation pairs. Tests on multiple data sets and domains show consistent accuracy improvements.&#8221;,Boosting neural machine translation with similar translations","protected":false},"excerpt":{"rendered":"<p>This presentation demonstrates data augmentation methods for Neural Machine Translation to make use of similar translations, in a comparable way a human translator employs fuzzy matches. We show how we simply feed the neural model with information on both source and target sides of the fuzzy matches, and we also extend the similarity to include &hellip; <a href=\"https:\/\/www-staging.systransoft.com\/es\/recursos\/papers-and-publications\/porro-in-qui-porro-ullam-adipisci-rem\/\">Continuaci\u00f3n<\/a><\/p>","protected":false},"featured_media":0,"template":"","class_list":["post-1697","paper","type-paper","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www-staging.systransoft.com\/es\/wp-json\/wp\/v2\/paper\/1697","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=1697"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}