{"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_with_a_benchmark_row":[{"paper":"/paper/lm-critic-language-models-for-unsupervised","title":"LM-Critic: Language Models for Unsupervised Grammatical Error Correction","date":"2021-09-14","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/neural-quality-estimation-with-multiple","title":"Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction","date":"2021-05-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-grammatical-error-correction-via","title":"Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data","date":"2019-03-01","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/jointly-learning-to-label-sentences-and","title":"Jointly Learning to Label Sentences and Tokens","date":"2018-11-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/neural-quality-estimation-of-grammatical","title":"Neural Quality Estimation of Grammatical Error Correction","date":"2018-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/reaching-human-level-performance-in-automatic","title":"Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study","date":"2018-07-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/near-human-level-performance-in-grammatical","title":"Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation","date":"2018-04-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/approaching-neural-grammatical-error","title":"Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task","date":"2018-04-16","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/a-multilayer-convolutional-encoder-decoder","title":"A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction","date":"2018-01-26","rows_on_this_dataset":3,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}