{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/levenshtein-transformer","title":"Levenshtein Transformer","arxiv_id":"1905.11006","date":"2019-05-27","proceeding":"NeurIPS 2019 12","authors":["Jiatao Gu","Changhan Wang","Jake Zhao"],"abstract":"Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new partially autoregressive model devised for more flexible and amenable sequence generation. Unlike previous approaches, the atomic operations of our model are insertion and deletion. The combination of them facilitates not only generation but also sequence refinement allowing dynamic length changes. We also propose a set of new training techniques dedicated at them, effectively exploiting one as the other's learning signal thanks to their complementary nature. Experiments applying the proposed model achieve comparable performance but much-improved efficiency on both generation (e.g. machine translation, text summarization) and refinement tasks (e.g. automatic post-editing). We further confirm the flexibility of our model by showing a Levenshtein Transformer trained by machine translation can straightforwardly be used for automatic post-editing.","url_abs":"https://arxiv.org/abs/1905.11006v2","url_pdf":"https://arxiv.org/pdf/1905.11006v2.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":"levenshtein-transformer","repo_url":"https://github.com/pytorch/fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"levenshtein-transformer","repo_url":"https://github.com/ictnlp/Seq-NAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"levenshtein-transformer","repo_url":"https://github.com/maxwell1447/fairseq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automatic-post-editing","task_name":"Automatic Post-Editing"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"text-summarization","task_name":"Text Summarization"},{"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":"levenshtein-transformer","method_name":"Levenshtein Transformer"},{"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":[{"slug":"levenshtein-transformer","name":"Levenshtein Transformer","full_name":"Levenshtein Transformer"}],"results":[{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Levenshtein Transformer (distillation)","rank_in_archive_order":52,"of":91,"metrics":{"BLEU score":"27.27"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset":"WMT2016 Romanian-English","model":"Levenshtein Transformer (distillation)","rank_in_archive_order":7,"of":21,"metrics":{"BLEU score":"33.26"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.11006","atlas_url":"https://app.syntology.ai/?focus=1905.11006","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1905.11006"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1905.11006\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1905.11006"},"call":"get_concepts_for_paper(arxiv_id=\"1905.11006\")"}],"by_repo":[{"repo":"pytorch/fairseq","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2105.08206","2105.14850","2203.09163"],"harvested_for_calls":[{"arxiv_id":"2105.08206","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.08206"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.08206\")"},{"arxiv_id":"2105.14850","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14850"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14850\")"},{"arxiv_id":"2203.09163","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09163"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09163\")"}]},{"repo":"ictnlp/Seq-NAT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.08122"],"harvested_for_calls":[{"arxiv_id":"2106.08122","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.08122"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.08122\")"}]},{"repo":"maxwell1447/fairseq","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2310.08967"],"harvested_for_calls":[{"arxiv_id":"2310.08967","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.08967"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.08967\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"11837e6e7c586f71871cae63c8a3dea774c215ea0ac57cc1465c1b24676a366a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}