{"id":1702,"date":"2022-06-11T10:17:59","date_gmt":"2022-06-11T08:17:59","guid":{"rendered":"https:\/\/www-staging.systransoft.com\/papers\/et-ut-non-rerum-nobis\/"},"modified":"2023-11-16T18:21:30","modified_gmt":"2023-11-16T17:21:30","slug":"et-ut-non-rerum-nobis","status":"publish","type":"paper","link":"https:\/\/www-staging.systransoft.com\/kr\/resources\/papers-and-publications\/et-ut-non-rerum-nobis\/","title":{"rendered":"\ub3d9\uc801 \uc0d8\ud50c\ub9c1 \uae30\ubc95\uc744 \uc774\uc6a9\ud55c \uc2e0\uacbd\uae30\uacc4 \ubc88\uc5ed\uc5d0\uc11c\uc758 \ub2e4\uc911 \uc601\uc5ed \uc801\uc751"},"content":{"rendered":"Building effective Neural Machine Translation models often implies accommodating diverse sets of heterogeneous data so as to optimize performance for the domain(s) of interest. Such multi-source \/ multi-domain adaptation problems are typically approached through instance selection or reweighting strategies, based on a static assessment of the relevance of training instances with respect to the task at hand. In this paper, we study dynamic data selection strategies that are able to automatically re-evaluate the usefulness of data samples and to evolve a data selection policy in the course of training. Based on the results of multiple experiments, we show that such methods constitute a generic framework to automatically and effectively handle a variety of real-world situations, from multi-source domain adaptation to multi-domain learning and unsupervised domain adaptation.","protected":false},"excerpt":{"rendered":"<p>\ud6a8\uacfc\uc801\uc778 \uc2e0\uacbd \uae30\uacc4 \ubc88\uc5ed \ubaa8\ub378\uc744 \uad6c\ucd95\ud558\ub294 \uac83\uc740 \uc885\uc885 \uad00\uc2ec \ub3c4\uba54\uc778(\ub4e4)\uc5d0 \ub300\ud55c \uc131\ub2a5\uc744 \ucd5c\uc801\ud654\ud558\uae30 \uc704\ud574 \ub2e4\uc591\ud55c \uc774\uc885 \ub370\uc774\ud130 \uc138\ud2b8\ub97c \uc218\uc6a9\ud558\ub294 \uac83\uc744 \uc758\ubbf8\ud55c\ub2e4. \uc774\ub7ec\ud55c \uba40\ud2f0-\uc18c\uc2a4\/\uba40\ud2f0-\ub3c4\uba54\uc778 \uc801\uc751 \ubb38\uc81c\ub4e4\uc740 \uc804\ud615\uc801\uc73c\ub85c, \ud0dc\uc2a4\ud06c\uc5d0 \uad00\ud55c \ud2b8\ub808\uc774\ub2dd \uc778\uc2a4\ud134\uc2a4\ub4e4\uc758 \uad00\ub828\uc131\uc5d0 \ub300\ud55c \uc815\uc801 \ud3c9\uac00\uc5d0 \uae30\ucd08\ud558\uc5ec, \uc778\uc2a4\ud134\uc2a4 \uc120\ud0dd \ub610\ub294 \uc7ac\uac00\uc911\ud654 \uc804\ub7b5\ub4e4\uc744 \ud1b5\ud574 \uc811\uadfc\ub41c\ub2e4. <a href=\"https:\/\/www-staging.systransoft.com\/kr\/resources\/papers-and-publications\/et-ut-non-rerum-nobis\/\">\uacc4\uc18d\ub428<\/a><\/p>","protected":false},"featured_media":0,"template":"","class_list":["post-1702","paper","type-paper","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www-staging.systransoft.com\/kr\/wp-json\/wp\/v2\/paper\/1702","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www-staging.systransoft.com\/kr\/wp-json\/wp\/v2\/paper"}],"about":[{"href":"https:\/\/www-staging.systransoft.com\/kr\/wp-json\/wp\/v2\/types\/paper"}],"wp:attachment":[{"href":"https:\/\/www-staging.systransoft.com\/kr\/wp-json\/wp\/v2\/media?parent=1702"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}