{"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/flowseq-non-autoregressive-conditional","title":"FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow","arxiv_id":"1909.02480","date":"2019-09-05","proceeding":"IJCNLP 2019 11","authors":["Xuezhe Ma","Chunting Zhou","Xi-An Li","Graham Neubig","Eduard Hovy"],"abstract":"Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens. In contrast, non-autoregressive seq2seq models generate all tokens in one pass, which leads to increased efficiency through parallel processing on hardware such as GPUs. However, directly modeling the joint distribution of all tokens simultaneously is challenging, and even with increasingly complex model structures accuracy lags significantly behind autoregressive models. In this paper, we propose a simple, efficient, and effective model for non-autoregressive sequence generation using latent variable models. Specifically, we turn to generative flow, an elegant technique to model complex distributions using neural networks, and design several layers of flow tailored for modeling the conditional density of sequential latent variables. We evaluate this model on three neural machine translation (NMT) benchmark datasets, achieving comparable performance with state-of-the-art non-autoregressive NMT models and almost constant decoding time w.r.t the sequence length.","url_abs":"https://arxiv.org/abs/1909.02480v3","url_pdf":"https://arxiv.org/pdf/1909.02480v3.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":"flowseq-non-autoregressive-conditional","repo_url":"https://github.com/XuezheMax/flowseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"flowseq-non-autoregressive-conditional","repo_url":"https://github.com/keonlee9420/VAENAR-TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-german","task":"Machine Translation","dataset":"IWSLT2015 German-English","model":"FlowSeq-base","rank_in_archive_order":12,"of":15,"metrics":{"BLEU score":"24.75"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"FlowSeq-large (NPD n = 30)","rank_in_archive_order":72,"of":91,"metrics":{"BLEU score":"23.64"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"FlowSeq-large (NPD n = 15)","rank_in_archive_order":73,"of":91,"metrics":{"BLEU score":"23.14"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"FlowSeq-large (IWD n = 15)","rank_in_archive_order":74,"of":91,"metrics":{"BLEU score":"22.94"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"FlowSeq-large","rank_in_archive_order":77,"of":91,"metrics":{"BLEU score":"20.85"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"FlowSeq-base","rank_in_archive_order":83,"of":91,"metrics":{"BLEU score":"18.55"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-german-english","task":"Machine Translation","dataset":"WMT2014 German-English","model":"FlowSeq-large (NPD n = 30)","rank_in_archive_order":9,"of":16,"metrics":{"BLEU score":"28.29"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-german-english","task":"Machine Translation","dataset":"WMT2014 German-English","model":"FlowSeq-large (NPD n = 15)","rank_in_archive_order":10,"of":16,"metrics":{"BLEU score":"27.71"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-german-english","task":"Machine Translation","dataset":"WMT2014 German-English","model":"FlowSeq-large (IWD n=15)","rank_in_archive_order":11,"of":16,"metrics":{"BLEU score":"27.16"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-german-english","task":"Machine Translation","dataset":"WMT2014 German-English","model":"FlowSeq-large","rank_in_archive_order":13,"of":16,"metrics":{"BLEU score":"25.4"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-german-english","task":"Machine Translation","dataset":"WMT2014 German-English","model":"FlowSeq-base","rank_in_archive_order":14,"of":16,"metrics":{"BLEU score":"23.36"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset":"WMT2016 English-Romanian","model":"FlowSeq-large (NPD n = 30)","rank_in_archive_order":3,"of":21,"metrics":{"BLEU score":"32.35"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset":"WMT2016 English-Romanian","model":"FlowSeq-large (NPD n=15)","rank_in_archive_order":4,"of":21,"metrics":{"BLEU score":"31.97"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset":"WMT2016 English-Romanian","model":"FlowSeq-large (IWD n = 15)","rank_in_archive_order":5,"of":21,"metrics":{"BLEU score":"31.08"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset":"WMT2016 English-Romanian","model":"FlowSeq-large","rank_in_archive_order":8,"of":21,"metrics":{"BLEU score":"29.86"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset":"WMT2016 English-Romanian","model":"FlowSeq-base","rank_in_archive_order":11,"of":21,"metrics":{"BLEU score":"29.26"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset":"WMT2016 Romanian-English","model":"FlowSeq-large (NPD n = 30)","rank_in_archive_order":11,"of":21,"metrics":{"BLEU score":"32.91"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset":"WMT2016 Romanian-English","model":"FlowSeq-large (NPD n = 15)","rank_in_archive_order":14,"of":21,"metrics":{"BLEU score":"32.46"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset":"WMT2016 Romanian-English","model":"FlowSeq-large (IWD n = 15)","rank_in_archive_order":15,"of":21,"metrics":{"BLEU score":"32.03"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset":"WMT2016 Romanian-English","model":"FlowSeq-large","rank_in_archive_order":18,"of":21,"metrics":{"BLEU score":"30.69"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset":"WMT2016 Romanian-English","model":"FlowSeq-base","rank_in_archive_order":20,"of":21,"metrics":{"BLEU score":"30.16"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.02480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02480"}},"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/XuezheMax/flowseq","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/VAENAR-TTS","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"6890088b59086e6e","entry":"calc_bleu","repo":"XuezheMax/flowseq","repo_kind":"official","path":"experiments/translate.py","file_url":"https://github.com/XuezheMax/flowseq/blob/HEAD/experiments/translate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6890088b59086e6e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}