{"url":"/sota/text-simplification-on-turkcorpus","task":{"name":"Text Simplification","url":"/task/text-simplification","note":null},"dataset":{"name":"TurkCorpus","url":"/dataset/turkcorpus"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"**Text Simplification** is the task of reducing the complexity of the vocabulary and sentence structure of text while retaining its original meaning, with the goal of improving readability and understanding. Simplification has a variety of important societal applications, for example increasing accessibility for those with cognitive disabilities such as aphasia, dyslexia, and autism, or for non-native speakers and children with reading difficulties.\r\n\r\n\r\n<span class=\"description-source\">Source: [Multilingual Unsupervised Sentence Simplification](https://arxiv.org/abs/2005.00352)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["SARI (EASSE>=0.2.1)","BLEU","METEOR","FKGL","QuestEval (Reference-less, BERTScore)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"SARI (EASSE>=0.2.1)":null,"BLEU":"higher","METEOR":null,"FKGL":null,"QuestEval (Reference-less, BERTScore)":null}},"counts":{"rows":25,"rows_with_code":17,"rows_with_paper_page":25,"rows_dated":25,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GPT-175B (6 SARI-selected examples, high/low)","metrics":{"BLEU":"79.83","FKGL":"9.33","SARI (EASSE>=0.2.1)":"43.46"},"uses_additional_data":false,"paper_date":"2023-07-27","paper":"/paper/metric-based-in-context-learning-a-case-study","paper_url":"https://arxiv.org/abs/2307.14632v1","paper_title":"Metric-Based In-context Learning: A Case Study in Text Simplification","code":"https://github.com/nlp-ku/metric-based-in-context-learning","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MUSS (BART+ACCESS Supervised)","metrics":{"BLEU":"78.17","FKGL":"7.60","SARI (EASSE>=0.2.1)":"42.53"},"uses_additional_data":false,"paper_date":"2020-05-01","paper":"/paper/multilingual-unsupervised-sentence","paper_url":"https://arxiv.org/abs/2005.00352v2","paper_title":"MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases","code":"https://github.com/facebookresearch/muss","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"Control Prefixes (BART)","metrics":{"FKGL":"7.74","QuestEval (Reference-less, BERTScore)":"0.66","SARI (EASSE>=0.2.1)":"42.32"},"uses_additional_data":false,"paper_date":"2021-10-15","paper":"/paper/control-prefixes-for-text-generation","paper_url":"https://arxiv.org/abs/2110.08329v2","paper_title":"Control Prefixes for Parameter-Efficient Text Generation","code":"https://github.com/Yale-LILY/dart","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"TST","metrics":{"SARI (EASSE>=0.2.1)":"41.46"},"uses_additional_data":false,"paper_date":"2021-03-08","paper":"/paper/text-simplification-by-tagging","paper_url":"https://arxiv.org/abs/2103.05070v1","paper_title":"Text Simplification by Tagging","code":"https://github.com/grammarly/gector","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"ACCESS","metrics":{"BLEU":"72.53","SARI (EASSE>=0.2.1)":"41.38"},"uses_additional_data":false,"paper_date":"2019-10-07","paper":"/paper/controllable-sentence-simplification","paper_url":"https://arxiv.org/abs/1910.02677v3","paper_title":"Controllable Sentence Simplification","code":"https://github.com/facebookresearch/access","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"MUSS (BART+ACCESS Unsupervised)","metrics":{"FKGL":"8.79","SARI (EASSE>=0.2.1)":"40.85"},"uses_additional_data":false,"paper_date":"2020-05-01","paper":"/paper/multilingual-unsupervised-sentence","paper_url":"https://arxiv.org/abs/2005.00352v2","paper_title":"MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases","code":"https://github.com/facebookresearch/muss","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"DMASS-DCSS","metrics":{"SARI (EASSE>=0.2.1)":"40.45"},"uses_additional_data":false,"paper_date":"2018-10-26","paper":"/paper/integrating-transformer-and-paraphrase-rules","paper_url":"http://arxiv.org/abs/1810.11193v1","paper_title":"Integrating Transformer and Paraphrase Rules for Sentence Simplification","code":"https://github.com/Sanqiang/text_simplification","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"SBMT-SARI","metrics":{"BLEU":"73.08*","SARI (EASSE>=0.2.1)":"39.56"},"uses_additional_data":false,"paper_date":"2016-01-01","paper":"/paper/optimizing-statistical-machine-translation","paper_url":"https://aclanthology.org/Q16-1029","paper_title":"Optimizing Statistical Machine Translation for Text Simplification","code":"https://github.com/cocoxu/simplification","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"EditNTS","metrics":{"BLEU":"86.69","SARI (EASSE>=0.2.1)":"38.22"},"uses_additional_data":false,"paper_date":"2019-06-19","paper":"/paper/editnts-an-neural-programmer-interpreter","paper_url":"https://arxiv.org/abs/1906.08104v1","paper_title":"EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing","code":"https://github.com/yuedongP/EditNTS","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"PBMT-R","metrics":{"SARI (EASSE>=0.2.1)":"38.04"},"uses_additional_data":false,"paper_date":"2012-07-01","paper":"/paper/sentence-simplification-by-monolingual","paper_url":"https://aclanthology.org/P12-1107","paper_title":"Sentence Simplification by Monolingual Machine Translation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"Edit-Unsup-TS","metrics":{"BLEU":"73.62","SARI (EASSE>=0.2.1)":"37.85"},"uses_additional_data":false,"paper_date":"2020-06-17","paper":"/paper/iterative-edit-based-unsupervised-sentence","paper_url":"https://arxiv.org/abs/2006.09639v1","paper_title":"Iterative Edit-Based Unsupervised Sentence Simplification","code":"https://github.com/ddhruvkr/Edit-Unsup-TS","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"Pointer + Multi-task Entailment and Paraphrase Generation","metrics":{"BLEU":"81.49","SARI (EASSE>=0.2.1)":"37.45"},"uses_additional_data":false,"paper_date":"2018-06-19","paper":"/paper/dynamic-multi-level-multi-task-learning-for","paper_url":"http://arxiv.org/abs/1806.07304v1","paper_title":"Dynamic Multi-Level Multi-Task Learning for Sentence Simplification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"Dress-LS","metrics":{"BLEU":"80.12","SARI (EASSE>=0.2.1)":"37.27"},"uses_additional_data":false,"paper_date":"2017-03-31","paper":"/paper/sentence-simplification-with-deep","paper_url":"http://arxiv.org/abs/1703.10931v2","paper_title":"Sentence Simplification with Deep Reinforcement Learning","code":"https://github.com/XingxingZhang/dress","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"NTS-SARI","metrics":{"BLEU":"80.69","SARI (EASSE>=0.2.1)":"37.25"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/exploring-neural-text-simplification-models","paper_url":"https://aclanthology.org/P17-2014","paper_title":"Exploring Neural Text Simplification Models","code":"https://github.com/senisioi/NeuralTextSimplification","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"UNMT (Unsupervised)","metrics":{"BLEU":"74.02","SARI (EASSE>=0.2.1)":"37.20"},"uses_additional_data":false,"paper_date":"2018-10-18","paper":"/paper/unsupervised-neural-text-simplification","paper_url":"https://arxiv.org/abs/1810.07931v6","paper_title":"Unsupervised Neural Text Simplification","code":"https://github.com/subramanyamdvss/UnsupNTS","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"UNTS-10k (Weakly supervised)","metrics":{"SARI (EASSE>=0.2.1)":"37.15"},"uses_additional_data":false,"paper_date":"2018-10-18","paper":"/paper/unsupervised-neural-text-simplification","paper_url":"https://arxiv.org/abs/1810.07931v6","paper_title":"Unsupervised Neural Text Simplification","code":"https://github.com/subramanyamdvss/UnsupNTS","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"Dress","metrics":{"BLEU":"77.18","SARI (EASSE>=0.2.1)":"37.08"},"uses_additional_data":false,"paper_date":"2017-03-31","paper":"/paper/sentence-simplification-with-deep","paper_url":"http://arxiv.org/abs/1703.10931v2","paper_title":"Sentence Simplification with Deep Reinforcement Learning","code":"https://github.com/XingxingZhang/dress","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"NSELSTM-S","metrics":{"BLEU":"80.43","SARI (EASSE>=0.2.1)":"36.88"},"uses_additional_data":false,"paper_date":"2018-04-20","paper":"/paper/sentence-simplification-with-memory-augmented","paper_url":"http://arxiv.org/abs/1804.07445v1","paper_title":"Sentence Simplification with Memory-Augmented Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"SEMoses","metrics":{"BLEU":"74.49","SARI (EASSE>=0.2.1)":"36.70"},"uses_additional_data":false,"paper_date":"2018-10-11","paper":"/paper/simple-and-effective-text-simplification","paper_url":"http://arxiv.org/abs/1810.05104v1","paper_title":"Simple and Effective Text Simplification Using Semantic and Neural Methods","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"UNTS (Unsupervised)","metrics":{"SARI (EASSE>=0.2.1)":"36.29"},"uses_additional_data":false,"paper_date":"2018-10-18","paper":"/paper/unsupervised-neural-text-simplification","paper_url":"https://arxiv.org/abs/1810.07931v6","paper_title":"Unsupervised Neural Text Simplification","code":"https://github.com/subramanyamdvss/UnsupNTS","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"NSELSTM-B","metrics":{"BLEU":"92.02","SARI (EASSE>=0.2.1)":"33.43"},"uses_additional_data":false,"paper_date":"2018-04-20","paper":"/paper/sentence-simplification-with-memory-augmented","paper_url":"http://arxiv.org/abs/1804.07445v1","paper_title":"Sentence Simplification with Memory-Augmented Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"T5","metrics":{"METEOR":"0.649"},"uses_additional_data":false,"paper_date":"2021-02-02","paper":"/paper/the-gem-benchmark-natural-language-generation","paper_url":"https://arxiv.org/abs/2102.01672v3","paper_title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"BART","metrics":{"METEOR":"0.556"},"uses_additional_data":false,"paper_date":"2021-02-02","paper":"/paper/the-gem-benchmark-natural-language-generation","paper_url":"https://arxiv.org/abs/2102.01672v3","paper_title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"Hybrid","metrics":{"BLEU":"48.97*","SARI (EASSE>=0.2.1)":"31.40*"},"uses_additional_data":false,"paper_date":"2014-06-01","paper":"/paper/hybrid-simplification-using-deep-semantics","paper_url":"https://aclanthology.org/P14-1041","paper_title":"Hybrid Simplification using Deep Semantics and Machine Translation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"SeqLabel","metrics":{"SARI (EASSE>=0.2.1)":"37.08*"},"uses_additional_data":false,"paper_date":"2017-11-01","paper":"/paper/learning-how-to-simplify-from-explicit","paper_url":"https://aclanthology.org/I17-1030","paper_title":"Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs","code":"https://github.com/ghpaetzold/massalign","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}