{"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/semi-autoregressive-neural-machine","title":"Semi-Autoregressive Neural Machine Translation","arxiv_id":"1808.08583","date":"2018-08-26","proceeding":"EMNLP 2018 10","authors":["Chunqi Wang","Ji Zhang","Haiqing Chen"],"abstract":"Existing approaches to neural machine translation are typically\nautoregressive models. While these models attain state-of-the-art translation\nquality, they are suffering from low parallelizability and thus slow at\ndecoding long sequences. In this paper, we propose a novel model for fast\nsequence generation --- the semi-autoregressive Transformer (SAT). The SAT\nkeeps the autoregressive property in global but relieves in local and thus is\nable to produce multiple successive words in parallel at each time step.\nExperiments conducted on English-German and Chinese-English translation tasks\nshow that the SAT achieves a good balance between translation quality and\ndecoding speed. On WMT'14 English-German translation, the SAT achieves\n5.58$\\times$ speedup while maintains 88\\% translation quality, significantly\nbetter than the previous non-autoregressive methods. When produces two words at\neach time step, the SAT is almost lossless (only 1\\% degeneration in BLEU\nscore).","url_abs":"http://arxiv.org/abs/1808.08583v2","url_pdf":"http://arxiv.org/pdf/1808.08583v2.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":"semi-autoregressive-neural-machine","repo_url":"https://github.com/chqiwang/sa-nmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.08583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.08583"}},"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/chqiwang/sa-nmt","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"3ad1487952836d07","entry":"average_gradients","repo":"chqiwang/sa-nmt","repo_kind":"official","path":"utils.py","file_url":"https://github.com/chqiwang/sa-nmt/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ad1487952836d07"}},{"code_sha256_prefix":"36fd928848e6906c","entry":"decoder_self_attention_bias","repo":"chqiwang/sa-nmt","repo_kind":"official","path":"models/sat.py","file_url":"https://github.com/chqiwang/sa-nmt/blob/HEAD/models/sat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"36fd928848e6906c"}},{"code_sha256_prefix":"d06bd91b2997aec4","entry":"expand_feed_dict","repo":"chqiwang/sa-nmt","repo_kind":"official","path":"utils.py","file_url":"https://github.com/chqiwang/sa-nmt/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d06bd91b2997aec4"}},{"code_sha256_prefix":"3b8288c2246709d7","entry":"pad_begin","repo":"chqiwang/sa-nmt","repo_kind":"official","path":"models/sat.py","file_url":"https://github.com/chqiwang/sa-nmt/blob/HEAD/models/sat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b8288c2246709d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}