{"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/very-deep-transformers-for-neural-machine","title":"Very Deep Transformers for Neural Machine Translation","arxiv_id":"2008.07772","date":"2020-08-18","proceeding":null,"authors":["Xiaodong Liu","Kevin Duh","Liyuan Liu","Jianfeng Gao"],"abstract":"We explore the application of very deep Transformer models for Neural Machine Translation (NMT). Using a simple yet effective initialization technique that stabilizes training, we show that it is feasible to build standard Transformer-based models with up to 60 encoder layers and 12 decoder layers. These deep models outperform their baseline 6-layer counterparts by as much as 2.5 BLEU, and achieve new state-of-the-art benchmark results on WMT14 English-French (43.8 BLEU and 46.4 BLEU with back-translation) and WMT14 English-German (30.1 BLEU).The code and trained models will be publicly available at: https://github.com/namisan/exdeep-nmt.","url_abs":"https://arxiv.org/abs/2008.07772v2","url_pdf":"https://arxiv.org/pdf/2008.07772v2.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":"very-deep-transformers-for-neural-machine","repo_url":"https://github.com/namisan/exdeep-nmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"very-deep-transformers-for-neural-machine","repo_url":"https://github.com/LiyuanLucasLiu/Transforemr-Clinic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"very-deep-transformers-for-neural-machine","repo_url":"https://github.com/LiyuanLucasLiu/Transformer-Clinic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"very-deep-transformers-for-neural-machine","repo_url":"https://github.com/microsoft/deepnmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Transformer+BT (ADMIN init)","rank_in_archive_order":1,"of":57,"metrics":{"BLEU score":"46.4","SacreBLEU":"44.4"},"uses_additional_data":true},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Transformer (ADMIN init)","rank_in_archive_order":5,"of":57,"metrics":{"BLEU score":"43.8","SacreBLEU":"41.8"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Transformer (ADMIN init)","rank_in_archive_order":12,"of":91,"metrics":{"BLEU score":"30.1","Number of Params":"256M","SacreBLEU":"29.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.07772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.07772"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/namisan/exdeep-nmt","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/deepnmt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LiyuanLucasLiu/Transforemr-Clinic","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LiyuanLucasLiu/Transformer-Clinic","reach":null}],"summary":{"ran_draft_wrong":5,"ran":1,"unverified":3},"by_repo_kind":{"listed":{"samples":9,"ran":6,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"96cbb5e9ca5b6be0","entry":"Embedding","repo":"microsoft/deepnmt","repo_kind":"listed","path":"deepnmt/adv_transformer.py","file_url":"https://github.com/microsoft/deepnmt/blob/HEAD/deepnmt/adv_transformer.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96cbb5e9ca5b6be0"}},{"code_sha256_prefix":"8cd8cb0d1e9e63e4","entry":"Linear","repo":"microsoft/deepnmt","repo_kind":"listed","path":"deepnmt/transformer_layer.py","file_url":"https://github.com/microsoft/deepnmt/blob/HEAD/deepnmt/transformer_layer.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cd8cb0d1e9e63e4"}},{"code_sha256_prefix":"81e9530973deb9b1","entry":"dictolist","repo":"LiyuanLucasLiu/Transformer-Clinic","repo_kind":"listed","path":"fairseq/examples/translation_moe/score.py","file_url":"https://github.com/LiyuanLucasLiu/Transformer-Clinic/blob/HEAD/fairseq/examples/translation_moe/score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81e9530973deb9b1"}},{"code_sha256_prefix":"99de76104bad1fc9","entry":"last_n_checkpoints","repo":"microsoft/deepnmt","repo_kind":"listed","path":"nmt_eval/average_checkpoints.py","file_url":"https://github.com/microsoft/deepnmt/blob/HEAD/nmt_eval/average_checkpoints.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99de76104bad1fc9"}},{"code_sha256_prefix":"3ed3082e1ace0b17","entry":"load_ref","repo":"LiyuanLucasLiu/Transformer-Clinic","repo_kind":"listed","path":"fairseq/examples/translation_moe/score.py","file_url":"https://github.com/LiyuanLucasLiu/Transformer-Clinic/blob/HEAD/fairseq/examples/translation_moe/score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ed3082e1ace0b17"}},{"code_sha256_prefix":"874a757bff402af6","entry":"load_sys","repo":"LiyuanLucasLiu/Transformer-Clinic","repo_kind":"listed","path":"fairseq/examples/translation_moe/score.py","file_url":"https://github.com/LiyuanLucasLiu/Transformer-Clinic/blob/HEAD/fairseq/examples/translation_moe/score.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"874a757bff402af6"}},{"code_sha256_prefix":"c8d783d775fd71be","entry":"KL","repo":"microsoft/deepnmt","repo_kind":"listed","path":"deepnmt/adv_label_smoothed_cross_entropy.py","file_url":"https://github.com/microsoft/deepnmt/blob/HEAD/deepnmt/adv_label_smoothed_cross_entropy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8d783d775fd71be"}},{"code_sha256_prefix":"7cc2e301e30389d1","entry":"average_checkpoints","repo":"microsoft/deepnmt","repo_kind":"listed","path":"nmt_eval/average_checkpoints.py","file_url":"https://github.com/microsoft/deepnmt/blob/HEAD/nmt_eval/average_checkpoints.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7cc2e301e30389d1"}},{"code_sha256_prefix":"0084024f3f3086ec","entry":"label_smoothed_nll_loss","repo":"microsoft/deepnmt","repo_kind":"listed","path":"deepnmt/adv_label_smoothed_cross_entropy.py","file_url":"https://github.com/microsoft/deepnmt/blob/HEAD/deepnmt/adv_label_smoothed_cross_entropy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0084024f3f3086ec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}