{"id":1703,"date":"2021-11-13T05:11:54","date_gmt":"2021-11-13T04:11:54","guid":{"rendered":"https:\/\/www.systransoft.com\/papers\/quam-illo-odio-sit-aliquid-praesentium\/"},"modified":"2023-11-16T18:20:54","modified_gmt":"2023-11-16T17:20:54","slug":"quam-illo-odio-sit-aliquid-praesentium","status":"publish","type":"paper","link":"https:\/\/www.systransoft.com\/es\/recursos\/papers-and-publications\/quam-illo-odio-sit-aliquid-praesentium\/","title":{"rendered":"SYSTRAN @ WMT 2021: Tarea de Terminolog\u00eda"},"content":{"rendered":"This paper describes SYSTRAN submissions to the WMT 2021 terminology shared task. We participate in the English-to-French translation direction with a standard Transformer neural machine translation network that we enhance with the ability to dynamically include terminology constraints, a very common industrial practice. Two state-of-the-art terminology insertion methods are evaluated based (i) on the use of placeholders complemented with morphosyntactic annotation and (ii) on the use of target constraints injected in the source stream. Results show the suitability of the presented approaches in the evaluated scenario where terminology is used in a system trained on generic data only","protected":false},"excerpt":{"rendered":"<p>Este art\u00edculo describe las presentaciones de SYSTRAN a la tarea compartida de terminolog\u00eda WMT 2021. Participamos en la direcci\u00f3n de traducci\u00f3n del ingl\u00e9s al franc\u00e9s con una red de traducci\u00f3n autom\u00e1tica neuronal Transformer est\u00e1ndar que mejoramos con la capacidad de incluir din\u00e1micamente restricciones de terminolog\u00eda, una pr\u00e1ctica industrial muy com\u00fan. Se eval\u00faan dos m\u00e9todos de inserci\u00f3n terminol\u00f3gica de \u00faltima generaci\u00f3n basados en (i) el uso \u2026 <a href=\"https:\/\/www.systransoft.com\/es\/recursos\/papers-and-publications\/quam-illo-odio-sit-aliquid-praesentium\/\">Continuaci\u00f3n<\/a><\/p>","protected":false},"featured_media":0,"template":"","class_list":["post-1703","paper","type-paper","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.systransoft.com\/es\/wp-json\/wp\/v2\/paper\/1703","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.systransoft.com\/es\/wp-json\/wp\/v2\/paper"}],"about":[{"href":"https:\/\/www.systransoft.com\/es\/wp-json\/wp\/v2\/types\/paper"}],"wp:attachment":[{"href":"https:\/\/www.systransoft.com\/es\/wp-json\/wp\/v2\/media?parent=1703"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}