{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/incorporating-bert-into-neural-machine-1","title":"Incorporating BERT into Neural Machine Translation","arxiv_id":"2002.06823","date":"2020-02-17","proceeding":"ICLR 2020 1","authors":["Jinhua Zhu","Yingce Xia","Lijun Wu","Di He","Tao Qin","Wengang Zhou","Houqiang Li","Tie-Yan Liu"],"abstract":"The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks enough exploration. While BERT is more commonly used as fine-tuning instead of contextual embedding for downstream language understanding tasks, in NMT, our preliminary exploration of using BERT as contextual embedding is better than using for fine-tuning. This motivates us to think how to better leverage BERT for NMT along this direction. We propose a new algorithm named BERT-fused model, in which we first use BERT to extract representations for an input sequence, and then the representations are fused with each layer of the encoder and decoder of the NMT model through attention mechanisms. We conduct experiments on supervised (including sentence-level and document-level translations), semi-supervised and unsupervised machine translation, and achieve state-of-the-art results on seven benchmark datasets. Our code is available at \\url{https://github.com/bert-nmt/bert-nmt}.","url_abs":"https://arxiv.org/abs/2002.06823v1","url_pdf":"https://arxiv.org/pdf/2002.06823v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"incorporating-bert-into-neural-machine-1","repo_url":"https://github.com/bert-nmt/bert-nmt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"incorporating-bert-into-neural-machine-1","repo_url":"https://github.com/StuartCHAN/KARL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"incorporating-bert-into-neural-machine-1","repo_url":"https://github.com/vivekgohel56/Neural-machine-translation-english-to-polish","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-machine-translation","task_name":"Unsupervised Machine Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"BERT-fused NMT","rank_in_archive_order":7,"of":57,"metrics":{"BLEU score":"43.78"},"uses_additional_data":true},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"BERT-fused NMT","rank_in_archive_order":8,"of":91,"metrics":{"BLEU score":"30.75"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2014-2","task":"Unsupervised Machine Translation","dataset":"WMT2014 English-French","model":"BERT-fused NMT","rank_in_archive_order":1,"of":7,"metrics":{"BLEU":"38.27"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016-5","task":"Unsupervised Machine Translation","dataset":"WMT2016 English--Romanian","model":"BERT-fused NMT","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"36.02"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.06823","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}