{"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":"/dataset/jfleg","name":"JFLEG","full_name":"JHU FLuency-Extended GUG corpus","description_markdown":"JFLEG is for developing and evaluating grammatical error correction (GEC). Unlike other corpora, it represents a broad range of language proficiency levels and uses holistic fluency edits to not only correct grammatical errors but also make the original text more native sounding. \r\n\r\nSource: [JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction](https://arxiv.org/pdf/1702.04066v1.pdf)","description_withheld":null,"homepage":"https://github.com/keisks/jfleg","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/jfleg-a-fluency-corpus-and-benchmark-for","title":"JFLEG: A Fluency Corpus and Benchmark for Grammatical Error Correction","first_author":"Courtney Napoles","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Grammatical Error Correction","url":"/task/grammatical-error-correction","datasets_with_task":"/datasets/task/grammatical-error-correction"},{"name":"Grammatical Error Detection","url":"/task/grammatical-error-detection","datasets_with_task":"/datasets/task/grammatical-error-detection"}],"languages":[],"variants":["JFLEG","Restricted","Unrestricted","_Restricted_"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jhu-clsp/jfleg","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jfleg","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/keisks/jfleg","url":"https://github.com/keisks/jfleg","frameworks":[]}],"num_papers_in_archive":91,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/grammatical-error-correction-on-jfleg","task":"Grammatical Error Correction","dataset_variant":"JFLEG","rows":6,"metrics":["GLEU"],"first_row_in_archive_order":{"model":"VERNet","paper":"/paper/neural-quality-estimation-with-multiple","metrics":{"GLEU":"62.1"},"code_links":[{"title":"thunlp/VERNet","url":"https://github.com/thunlp/VERNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/grammatical-error-correction-on-restricted","task":"Grammatical Error Correction","dataset_variant":"Restricted","rows":4,"metrics":["F0.5"],"first_row_in_archive_order":{"model":"CNN Seq2Seq","paper":"/paper/a-multilayer-convolutional-encoder-decoder","metrics":{"F0.5":"70.14 (measured by Ge et al., 2018)"},"code_links":[{"title":"nusnlp/mlconvgec2018","url":"https://github.com/nusnlp/mlconvgec2018"},{"title":"seaweiqing/neuraltalk_plus_charcnn","url":"https://github.com/seaweiqing/neuraltalk_plus_charcnn"},{"title":"seaweiqing/image2story","url":"https://github.com/seaweiqing/image2story"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/grammatical-error-correction-on-unrestricted","task":"Grammatical Error Correction","dataset_variant":"Unrestricted","rows":3,"metrics":["F0.5","GLEU"],"first_row_in_archive_order":{"model":"CNN Seq2Seq + Fluency Boost","paper":"/paper/reaching-human-level-performance-in-automatic","metrics":{"F0.5":"61.34"},"code_links":[{"title":"getao/human-performance-gec","url":"https://github.com/getao/human-performance-gec"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/grammatical-error-correction-on-_restricted_","task":"Grammatical Error Correction","dataset_variant":"_Restricted_","rows":2,"metrics":["GLEU"],"first_row_in_archive_order":{"model":"Transformer","paper":"/paper/approaching-neural-grammatical-error","metrics":{"GLEU":"59.9"},"code_links":[{"title":"grammatical/neural-naacl2018","url":"https://github.com/grammatical/neural-naacl2018"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/grammatical-error-detection-on-jfleg","task":"Grammatical Error Detection","dataset_variant":"JFLEG","rows":1,"metrics":["F0.5"],"first_row_in_archive_order":{"model":"BiLSTM-JOINT (trained on FCE)","paper":"/paper/jointly-learning-to-label-sentences-and","metrics":{"F0.5":"52.52"},"code_links":[{"title":"marekrei/mltagger","url":"https://github.com/marekrei/mltagger"},{"title":"MirunaPislar/multi-head-attention-labeller","url":"https://github.com/MirunaPislar/multi-head-attention-labeller"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":10,"of":10,"counts":{"papers_with_a_benchmark_row":10,"with_a_code_link":9,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":10,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/lm-critic-language-models-for-unsupervised","slug":"lm-critic-language-models-for-unsupervised","title":"LM-Critic: Language Models for Unsupervised Grammatical Error Correction","date":"2021-09-14","arxiv_id":"2109.06822","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/neural-quality-estimation-with-multiple","slug":"neural-quality-estimation-with-multiple","title":"Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction","date":"2021-05-10","arxiv_id":"2105.04443","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/encoder-decoder-models-can-benefit-from-pre","slug":"encoder-decoder-models-can-benefit-from-pre","title":"Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction","date":"2020-05-03","arxiv_id":"2005.00987","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-grammatical-error-correction-via","slug":"improving-grammatical-error-correction-via","title":"Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data","date":"2019-03-01","arxiv_id":"1903.00138","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/jointly-learning-to-label-sentences-and","slug":"jointly-learning-to-label-sentences-and","title":"Jointly Learning to Label Sentences and Tokens","date":"2018-11-14","arxiv_id":"1811.05949","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/neural-quality-estimation-of-grammatical","slug":"neural-quality-estimation-of-grammatical","title":"Neural Quality Estimation of Grammatical Error Correction","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/reaching-human-level-performance-in-automatic","slug":"reaching-human-level-performance-in-automatic","title":"Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study","date":"2018-07-03","arxiv_id":"1807.01270","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/approaching-neural-grammatical-error","slug":"approaching-neural-grammatical-error","title":"Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task","date":"2018-04-16","arxiv_id":"1804.05940","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/near-human-level-performance-in-grammatical","slug":"near-human-level-performance-in-grammatical","title":"Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation","date":"2018-04-16","arxiv_id":"1804.05945","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-multilayer-convolutional-encoder-decoder","slug":"a-multilayer-convolutional-encoder-decoder","title":"A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction","date":"2018-01-26","arxiv_id":"1801.08831","rows_on_this_dataset":3,"code_links":3,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/lm-critic-language-models-for-unsupervised","slug":"lm-critic-language-models-for-unsupervised","title":"LM-Critic: Language Models for Unsupervised Grammatical Error Correction","date":"2021-09-14","arxiv_id":"2109.06822","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/neural-quality-estimation-with-multiple","slug":"neural-quality-estimation-with-multiple","title":"Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction","date":"2021-05-10","arxiv_id":"2105.04443","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/encoder-decoder-models-can-benefit-from-pre","slug":"encoder-decoder-models-can-benefit-from-pre","title":"Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction","date":"2020-05-03","arxiv_id":"2005.00987","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-grammatical-error-correction-via","slug":"improving-grammatical-error-correction-via","title":"Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data","date":"2019-03-01","arxiv_id":"1903.00138","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/jointly-learning-to-label-sentences-and","slug":"jointly-learning-to-label-sentences-and","title":"Jointly Learning to Label Sentences and Tokens","date":"2018-11-14","arxiv_id":"1811.05949","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/neural-quality-estimation-of-grammatical","slug":"neural-quality-estimation-of-grammatical","title":"Neural Quality Estimation of Grammatical Error Correction","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/reaching-human-level-performance-in-automatic","slug":"reaching-human-level-performance-in-automatic","title":"Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study","date":"2018-07-03","arxiv_id":"1807.01270","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/approaching-neural-grammatical-error","slug":"approaching-neural-grammatical-error","title":"Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task","date":"2018-04-16","arxiv_id":"1804.05940","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/near-human-level-performance-in-grammatical","slug":"near-human-level-performance-in-grammatical","title":"Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation","date":"2018-04-16","arxiv_id":"1804.05945","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-multilayer-convolutional-encoder-decoder","slug":"a-multilayer-convolutional-encoder-decoder","title":"A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction","date":"2018-01-26","arxiv_id":"1801.08831","rows_on_this_dataset":3,"code_links":3,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/grammatical-error-correction-on-jfleg","since_archive":"/sota/grammatical-error-correction-on-jfleg#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"13c77f90b4ca44cc568b08aac96fb58605eb7a7c9f6fd5262f21b6bfc241419c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}