{"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/weighted-transformer-network-for-machine","title":"Weighted Transformer Network for Machine Translation","arxiv_id":"1711.02132","date":"2017-11-06","proceeding":"ICLR 2018 1","authors":["Karim Ahmed","Nitish Shirish Keskar","Richard Socher"],"abstract":"State-of-the-art results on neural machine translation often use attentional\nsequence-to-sequence models with some form of convolution or recursion. Vaswani\net al. (2017) propose a new architecture that avoids recurrence and convolution\ncompletely. Instead, it uses only self-attention and feed-forward layers. While\nthe proposed architecture achieves state-of-the-art results on several machine\ntranslation tasks, it requires a large number of parameters and training\niterations to converge. We propose Weighted Transformer, a Transformer with\nmodified attention layers, that not only outperforms the baseline network in\nBLEU score but also converges 15-40% faster. Specifically, we replace the\nmulti-head attention by multiple self-attention branches that the model learns\nto combine during the training process. Our model improves the state-of-the-art\nperformance by 0.5 BLEU points on the WMT 2014 English-to-German translation\ntask and by 0.4 on the English-to-French translation task.","url_abs":"http://arxiv.org/abs/1711.02132v1","url_pdf":"http://arxiv.org/pdf/1711.02132v1.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":"weighted-transformer-network-for-machine","repo_url":"https://github.com/Flawless1202/Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"weighted-transformer-network-for-machine","repo_url":"https://github.com/JayParks/transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"weighted-transformer-network-for-machine","repo_url":"https://github.com/bagequan/tencent-transformer-with-disagreement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"weighted-transformer-network-for-machine","repo_url":"https://github.com/duyvuleo/Transformer-DyNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"weighted-transformer-network-for-machine","repo_url":"https://github.com/xrick/PyTorch_Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"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":"convolution","method_name":"Convolution"},{"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":"relu","method_name":"ReLU"},{"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":"Weighted Transformer (large)","rank_in_archive_order":24,"of":57,"metrics":{"BLEU score":"41.4"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Weighted Transformer (large)","rank_in_archive_order":36,"of":91,"metrics":{"BLEU score":"28.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.02132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.02132"}},"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/duyvuleo/Transformer-DyNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bagequan/tencent-transformer-with-disagreement","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JayParks/transformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Flawless1202/Transformer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xrick/PyTorch_Transformer","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran_honours":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"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":2,"samples":[{"code_sha256_prefix":"4ca45d955a900746","entry":"get_attn_subsequent_mask","repo":"JayParks/transformer","repo_kind":"listed","path":"transformer/models.py","file_url":"https://github.com/JayParks/transformer/blob/HEAD/transformer/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4ca45d955a900746"}},{"code_sha256_prefix":"b416d5c73b835ba8","entry":"proj_prob_simplex","repo":"JayParks/transformer","repo_kind":"listed","path":"transformer/models.py","file_url":"https://github.com/JayParks/transformer/blob/HEAD/transformer/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b416d5c73b835ba8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}