{"url":"/task/text-simplification","name":"Text Simplification","slug":"text-simplification","description_markdown":"**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>","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":468,"papers_with_code":129,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":20,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-simplification-on-turkcorpus","slug":"text-simplification-on-turkcorpus","dataset":"TurkCorpus","dataset_url":"/dataset/turkcorpus","rows_in_archive":25,"metrics":["SARI (EASSE>=0.2.1)","BLEU","METEOR","FKGL","QuestEval (Reference-less, BERTScore)"],"first_row_in_archive_order":{"model":"GPT-175B (6 SARI-selected examples, high/low)","paper_title":"Metric-Based In-context Learning: A Case Study in Text Simplification","paper_url":"/paper/metric-based-in-context-learning-a-case-study","paper_date":"2023-07-27","arxiv_id":"2307.14632","code_links":[{"title":"nlp-ku/metric-based-in-context-learning","url":"https://github.com/nlp-ku/metric-based-in-context-learning"}],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-newsela","slug":"text-simplification-on-newsela","dataset":"Newsela","dataset_url":"/dataset/newsela","rows_in_archive":13,"metrics":["SARI","BLEU"],"first_row_in_archive_order":{"model":"CRF Alignment + Transformer","paper_title":"Neural CRF Model for Sentence Alignment in Text Simplification","paper_url":"/paper/neural-crf-model-for-sentence-alignment-in","paper_date":"2020-05-05","arxiv_id":"2005.02324","code_links":[{"title":"chaojiang06/wiki-auto","url":"https://github.com/chaojiang06/wiki-auto"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/text-simplification-on-asset","slug":"text-simplification-on-asset","dataset":"ASSET","dataset_url":"/dataset/asset","rows_in_archive":12,"metrics":["BLEU","SARI (EASSE>=0.2.1)","METEOR","FKGL","QuestEval (Reference-less, BERTScore)"],"first_row_in_archive_order":{"model":"GPT-175B (15 SARI-selected examples, random ordering)","paper_title":"Metric-Based In-context Learning: A Case Study in Text Simplification","paper_url":"/paper/metric-based-in-context-learning-a-case-study","paper_date":"2023-07-27","arxiv_id":"2307.14632","code_links":[{"title":"nlp-ku/metric-based-in-context-learning","url":"https://github.com/nlp-ku/metric-based-in-context-learning"}],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-pwkp-wikismall","slug":"text-simplification-on-pwkp-wikismall","dataset":"PWKP / WikiSmall","dataset_url":null,"rows_in_archive":11,"metrics":["BLEU","SARI","SARI (EASSE>=0.2.1)"],"first_row_in_archive_order":{"model":"NSELSTM-B","paper_title":"Sentence Simplification with Memory-Augmented Neural Networks","paper_url":"/paper/sentence-simplification-with-memory-augmented","paper_date":"2018-04-20","arxiv_id":"1804.07445","code_links":[],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-deplain-apa-doc","slug":"text-simplification-on-deplain-apa-doc","dataset":"DEplain-APA-doc","dataset_url":"/dataset/deplain-apa-doc","rows_in_archive":3,"metrics":["SARI (EASSE>=0.2.1)","BLEU","BertScore (Precision)","FRE (Flesch Reading Ease)"],"first_row_in_archive_order":{"model":"long-mBART (trained on DEplain-APA-doc)","paper_title":"DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification","paper_url":"/paper/deplain-a-german-parallel-corpus-with","paper_date":"2023-05-30","arxiv_id":"2305.18939","code_links":[{"title":"rstodden/deplain","url":"https://github.com/rstodden/deplain"}],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-deplain-web-doc","slug":"text-simplification-on-deplain-web-doc","dataset":"DEplain-web-doc","dataset_url":"/dataset/deplain-web-doc","rows_in_archive":3,"metrics":["SARI (EASSE>=0.2.1)","BLEU","BertScore (Precision)","FRE (Flesch Reading Ease)"],"first_row_in_archive_order":{"model":"long-mBART (trained on DEplain-APA-doc & DEplain-web-doc)","paper_title":"DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification","paper_url":"/paper/deplain-a-german-parallel-corpus-with","paper_date":"2023-05-30","arxiv_id":"2305.18939","code_links":[{"title":"rstodden/deplain","url":"https://github.com/rstodden/deplain"}],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-eurekaalert","slug":"text-simplification-on-eurekaalert","dataset":"EurekaAlert","dataset_url":"/dataset/eurekaalert","rows_in_archive":3,"metrics":["Rouge1","SARI"],"first_row_in_archive_order":{"model":"MedTSS-BART (Without Training)","paper_title":"MedTSS: transforming abstractive summarization of scientific articles with linguistic analysis and concept reinforcement","paper_url":"/paper/medtss-transforming-abstractive-summarization","paper_date":"2024-01-30","arxiv_id":null,"code_links":[{"title":"NadiaSaeed/MedTSS","url":"https://github.com/NadiaSaeed/MedTSS"}],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-deplain-apa-sent","slug":"text-simplification-on-deplain-apa-sent","dataset":"DEplain-APA-sent","dataset_url":"/dataset/deplain","rows_in_archive":2,"metrics":["SARI (EASSE>=0.2.1)","BLEU","BertScore (Precision)","FRE (Flesch Reading Ease)"],"first_row_in_archive_order":{"model":"mBART (trained on DEplain-APA-sent & DEplain-web-sent)","paper_title":"DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification","paper_url":"/paper/deplain-a-german-parallel-corpus-with","paper_date":"2023-05-30","arxiv_id":"2305.18939","code_links":[{"title":"rstodden/deplain","url":"https://github.com/rstodden/deplain"}],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-deplain-web-sent","slug":"text-simplification-on-deplain-web-sent","dataset":"DEplain-web-sent","dataset_url":"/dataset/deplain-web-sent","rows_in_archive":2,"metrics":["SARI (EASSE>=0.2.1)","BLEU","BertScore (Precision)","FRE (Flesch Reading Ease)"],"first_row_in_archive_order":{"model":"mBART (trained on DEplain-APA-sent & DEplain-web-sent)","paper_title":"DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification","paper_url":"/paper/deplain-a-german-parallel-corpus-with","paper_date":"2023-05-30","arxiv_id":"2305.18939","code_links":[{"title":"rstodden/deplain","url":"https://github.com/rstodden/deplain"}],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-wikilargefr","slug":"text-simplification-on-wikilargefr","dataset":"WikiLargeFR","dataset_url":null,"rows_in_archive":2,"metrics":["SARI"],"first_row_in_archive_order":{"model":"mT5 (fine-tuned on MULTI-SIM)","paper_title":"Revisiting non-English Text Simplification: A Unified Multilingual Benchmark","paper_url":"/paper/revisiting-non-english-text-simplification-a","paper_date":"2023-05-25","arxiv_id":"2305.15678","code_links":[{"title":"xenonmolecule/multisim","url":"https://github.com/xenonmolecule/multisim"}],"syntology":null}},{"leaderboard":"/sota/text-simplification-on-wiki-auto-turk","slug":"text-simplification-on-wiki-auto-turk","dataset":"Wiki-Auto + Turk","dataset_url":null,"rows_in_archive":1,"metrics":["BLEU-4","METEOR","ROUGE-2"],"first_row_in_archive_order":{"model":"BART (TextBox 2.0)","paper_title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","paper_url":"/paper/textbox-2-0-a-text-generation-library-with","paper_date":"2022-12-26","arxiv_id":"2212.13005","code_links":[{"title":"RUCAIBox/TextBox","url":"https://github.com/RUCAIBox/TextBox"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/newsela","name":"Newsela","full_name":"","num_papers_in_archive":106},{"url":"/dataset/wikilarge","name":"WikiLarge","full_name":"","num_papers_in_archive":69},{"url":"/dataset/asset","name":"ASSET","full_name":"ASSET","num_papers_in_archive":54},{"url":"/dataset/turkcorpus","name":"TurkCorpus","full_name":"","num_papers_in_archive":44},{"url":"/dataset/onestopenglish","name":"OneStopEnglish","full_name":"","num_papers_in_archive":29},{"url":"/dataset/wikisplit","name":"WikiSplit","full_name":"","num_papers_in_archive":21},{"url":"/dataset/textcomplexityde","name":"TextComplexityDE","full_name":"","num_papers_in_archive":16},{"url":"/dataset/cefr-sp","name":"CEFR-SP","full_name":"","num_papers_in_archive":7},{"url":"/dataset/klexikon","name":"Klexikon","full_name":"Klexikon: A German Dataset for Joint Summarization and Simplification","num_papers_in_archive":5},{"url":"/dataset/eurekaalert","name":"EurekaAlert","full_name":"Eureka Alert","num_papers_in_archive":4},{"url":"/dataset/med-easi","name":"Med-EASi","full_name":"","num_papers_in_archive":4},{"url":"/dataset/textbox-2-0","name":"TextBox 2.0","full_name":"","num_papers_in_archive":3},{"url":"/dataset/deplain","name":"DEplain-APA-sent","full_name":"","num_papers_in_archive":2},{"url":"/dataset/deplain-web-sent","name":"DEplain-web-sent","full_name":"","num_papers_in_archive":2},{"url":"/dataset/deplain-apa-doc","name":"DEplain-APA-doc","full_name":"","num_papers_in_archive":1},{"url":"/dataset/deplain-web-doc","name":"DEplain-web-doc","full_name":"","num_papers_in_archive":1},{"url":"/dataset/infolossqa","name":"InfoLossQA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/medical-wiki-paralell-corpus-for-medical-text","name":"Medical Wiki Paralell Corpus for Medical Text Simplification","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mwe-cwi","name":"MWE-CWI","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/simpevalasset","name":"SimpEvalASSET","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":129,"tagged_in_all":468,"items":[{"url":"/paper/medgen-a-python-natural-language-processing","title":"Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation","date":"2023-11-28","arxiv_id":"2311.16588","repositories_listed":3,"syntology":null},{"url":"/paper/felix-flexible-text-editing-through-tagging","title":"Felix: Flexible Text Editing Through Tagging and Insertion","date":"2020-03-24","arxiv_id":"2003.10687","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/automatic-input-rewriting-improves","title":"Automatic Input Rewriting Improves Translation with Large Language Models","date":"2025-02-23","arxiv_id":"2502.16682","repositories_listed":2,"syntology":null},{"url":"/paper/tess-text-to-text-self-conditioned-simplex","title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion","date":"2023-05-15","arxiv_id":"2305.08379","repositories_listed":2,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/lossless-acceleration-for-seq2seq-generation","title":"Lossless Acceleration for Seq2seq Generation with Aggressive Decoding","date":"2022-05-20","arxiv_id":"2205.10350","repositories_listed":2,"syntology":null},{"url":"/paper/klexikon-a-german-dataset-for-joint","title":"Klexikon: A German Dataset for Joint Summarization and Simplification","date":"2022-01-18","arxiv_id":"2201.07198","repositories_listed":2,"syntology":null},{"url":"/paper/control-prefixes-for-text-generation","title":"Control Prefixes for Parameter-Efficient Text Generation","date":"2021-10-15","arxiv_id":"2110.08329","repositories_listed":2,"syntology":null},{"url":"/paper/htss-a-novel-hybrid-text-summarisation-and","title":"HTSS: A Novel Hybrid Text Summarisation and Simplification Architecture","date":"2020-07-13","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/controllable-sentence-simplification","title":"Controllable Sentence Simplification","date":"2019-10-07","arxiv_id":"1910.02677","repositories_listed":2,"syntology":null},{"url":"/paper/complexity-weighted-loss-and-diverse","title":"Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification","date":"2019-04-04","arxiv_id":"1904.02767","repositories_listed":2,"syntology":null},{"url":"/paper/discofuse-a-large-scale-dataset-for-discourse","title":"DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion","date":"2019-02-27","arxiv_id":"1902.10526","repositories_listed":2,"syntology":null},{"url":"/paper/document-level-text-generation-with-minimum","title":"Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport","date":"2025-05-29","arxiv_id":"2505.23078","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-paraphrase-type-generation-the","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","date":"2025-05-28","arxiv_id":"2506.02018","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-sentence-simplification-with-esl","title":"Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition","date":"2025-02-17","arxiv_id":"2502.11457","repositories_listed":1,"syntology":null},{"url":"/paper/sitse-sinhala-text-simplification-dataset-and","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","date":"2024-12-02","arxiv_id":"2412.01293","repositories_listed":1,"syntology":null},{"url":"/paper/bertscorevisualizer-a-web-tool-for","title":"BERTScoreVisualizer: A Web Tool for Understanding Simplified Text Evaluation with BERTScore","date":"2024-09-10","arxiv_id":"2409.17160","repositories_listed":1,"syntology":null},{"url":"/paper/two-pronged-human-evaluation-of-chatgpt-self","title":"Two-Pronged Human Evaluation of ChatGPT Self-Correction in Radiology Report Simplification","date":"2024-06-27","arxiv_id":"2406.18859","repositories_listed":1,"syntology":null},{"url":"/paper/simpler-becomes-harder-do-llms-exhibit-a","title":"Simpler becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora?","date":"2024-04-10","arxiv_id":"2404.06838","repositories_listed":1,"syntology":null},{"url":"/paper/easse-de-easier-automatic-sentence","title":"EASSE-DE: Easier Automatic Sentence Simplification Evaluation for German","date":"2024-04-04","arxiv_id":"2404.03563","repositories_listed":1,"syntology":null},{"url":"/paper/referee-a-reference-free-model-based-metric","title":"REFeREE: A REference-FREE Model-Based Metric for Text Simplification","date":"2024-03-26","arxiv_id":"2403.17640","repositories_listed":1,"syntology":null},{"url":"/paper/artist-automated-text-simplification-for-task","title":"ARTiST: Automated Text Simplification for Task Guidance in Augmented Reality","date":"2024-02-29","arxiv_id":"2402.18797","repositories_listed":1,"syntology":null},{"url":"/paper/medit-multilingual-text-editing-via","title":"mEdIT: Multilingual Text Editing via Instruction Tuning","date":"2024-02-26","arxiv_id":"2402.16472","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/german-text-simplification-finetuning-large","title":"German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data","date":"2024-02-16","arxiv_id":"2402.10675","repositories_listed":1,"syntology":null},{"url":"/paper/medtss-transforming-abstractive-summarization","title":"MedTSS: transforming abstractive summarization of scientific articles with linguistic analysis and concept reinforcement","date":"2024-01-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/infolossqa-characterizing-and-recovering","title":"InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification","date":"2024-01-29","arxiv_id":"2401.16475","repositories_listed":1,"syntology":null},{"url":"/paper/health-text-simplification-an-annotated","title":"Health Text Simplification: An Annotated Corpus for Digestive Cancer Education and Novel Strategies for Reinforcement Learning","date":"2024-01-26","arxiv_id":"2401.15043","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-automatic-text-simplification-of","title":"Exploring Automatic Text Simplification of German Narrative Documents","date":"2023-12-15","arxiv_id":"2312.09907","repositories_listed":1,"syntology":null},{"url":"/paper/do-text-simplification-systems-preserve","title":"Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension","date":"2023-12-15","arxiv_id":"2312.10126","repositories_listed":1,"syntology":null},{"url":"/paper/bless-benchmarking-large-language-models-on","title":"BLESS: Benchmarking Large Language Models on Sentence Simplification","date":"2023-10-24","arxiv_id":"2310.15773","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/evaluation-metrics-in-the-era-of-gpt-4","title":"Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks","date":"2023-10-20","arxiv_id":"2310.13800","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}