{"id":3158,"date":"2020-07-17T16:43:47","date_gmt":"2020-07-17T14:43:47","guid":{"rendered":"https:\/\/www-staging.systransoft.com\/?post_type=paper&#038;p=3158"},"modified":"2023-11-16T18:19:42","modified_gmt":"2023-11-16T17:19:42","slug":"efficient-and-high-quality-neural-machine-translation-with-opennmt","status":"publish","type":"paper","link":"https:\/\/www-staging.systransoft.com\/jp\/resources\/papers-and-publications\/efficient-and-high-quality-neural-machine-translation-with-opennmt\/","title":{"rendered":"Efficient and High-Quality Neural Machine Translation with OpenNMT"},"content":{"rendered":"<p>This paper describes the OpenNMT submissions to the WNGT 2020 efficiency shared task. We explore training and acceleration of Transformer models with various sizes that are trained in a teacher-student setup. We also present a custom and optimized C++ inference engine that enables fast CPU and GPU decoding with few dependencies. By combining additional optimizations and parallelization techniques, we create small, efficient, and high-quality neural machine translation models.<\/p>","protected":false},"excerpt":{"rendered":"<p>This paper describes the OpenNMT submissions to the WNGT 2020 efficiency shared task. We explore training and acceleration of Transformer models with various sizes that are trained in a teacher-student setup. We also present a custom and optimized C++ inference engine that enables fast CPU and GPU decoding with few dependencies. By combining additional optimizations and parallelization techniques, we create small, efficient, and high-quality neural machine translation models.<\/p>","protected":false},"featured_media":0,"template":"","class_list":["post-3158","paper","type-paper","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www-staging.systransoft.com\/jp\/wp-json\/wp\/v2\/paper\/3158","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www-staging.systransoft.com\/jp\/wp-json\/wp\/v2\/paper"}],"about":[{"href":"https:\/\/www-staging.systransoft.com\/jp\/wp-json\/wp\/v2\/types\/paper"}],"wp:attachment":[{"href":"https:\/\/www-staging.systransoft.com\/jp\/wp-json\/wp\/v2\/media?parent=3158"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}