\n\t

\n\t\tBridging the Gap between Training and Inference for Neural Machine Translation\n\t<\/p>\n\t

\n\t\tWen Zhang, Yang Feng, Fandong Meng, Di You, Qun Liu\n\t<\/p>\n\t

\n\t\tAbstract\n\t<\/p>\n\t

\n\t\tNeural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context leads to error accumulation among the way. Furthermore, word-level training requires strict matching between the generated sequence and the ground truth sequence which leads to overcorrection over different but reasonable translations. In this paper, we address these issues by sampling context words not only from the ground truth sequence but also from the predicted sequence by the model during training, where the predicted sequence is selected with a sentence-level optimum. Experiment results on Chinese!English and WMT\u201914 English!German translation tasks demonstrate that our approach can achieve significant improvements on multiple datasets.\n\t<\/p>\n<\/div>\n\n\n\n

Bridging-the-Gap-between-Training-and-Inference-for-Neural-Machine-Translation<\/a>\u4e0b\u8f7d<\/a><\/div>\n\n\n\n\n\n\n\n

NLPIR SEMINAR 38th ISSUE COMPLETED<\/strong><\/h2>\n\n\n\n
This Monday, Yaofei Yang shared a lecture on the best long paper of ACL 2019.<\/p>\n\n\n\n
$\"\"$ <\/figure><\/div>\n\n\n\n
Here is ppt for this seminar.<\/p>\n\n\n\n
bridge<\/a>\u4e0b\u8f7d<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"
NLPIR SEMINAR Y2019#26 INTRO In the new … \u7ee7\u7eed\u9605\u8bfb →<\/span><\/a><\/p>\n","protected":false},"author":862,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[37,38],"tags":[],"_links":{"self":[{"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/posts\/7014"}],"collection":[{"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/users\/862"}],"replies":[{"embeddable":true,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/comments?post=7014"}],"version-history":[{"count":4,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/posts\/7014\/revisions"}],"predecessor-version":[{"id":7034,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/posts\/7014\/revisions\/7034"}],"wp:attachment":[{"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/media?parent=7014"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/categories?post=7014"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.nlpir.org\/wordpress\/wp-json\/wp\/v2\/tags?post=7014"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

INTRO<\/h3>\n\n\n\n In the new semester, our Lab, Web Search Mining and Security Lab, plans to hold an academic seminar every Monday, and each time a keynote speaker will share understanding of papers on his\/her related research with you.<\/p>\n\n\n\n

NLPIR SEMINAR 38th ISSUE COMPLETED<\/strong><\/h2>\n\n\n\nThis Monday, Yaofei Yang shared a lecture on the best long paper of ACL 2019.<\/p>\n\n\n\n<\/figure><\/div>\n\n\n\nHere is ppt for this seminar.<\/p>\n\n\n\n

INTRO<\/h3>\n\n\n\n
In the new semester, our Lab, Web Search Mining and Security Lab, plans to hold an academic seminar every Monday, and each time a keynote speaker will share understanding of papers on his\/her related research with you.<\/p>\n\n\n\n