{"url":"/dataset/newsela","name":"Newsela","full_name":null,"description_markdown":"The **Newsela dataset** was introduced by Xu et al. in their research on text simplification. It is a corpus that includes thousands of news articles professionally leveled to different reading complexities. The dataset is used for academic research in fields such as text difficulty and text simplification. It is made available to academic partners upon request. The dataset is often used as a benchmark in the field of text simplification. Please note that the Newsela dataset is different from the NELA datasets, which are collections of news articles for the study of media bias and other applications.","description_withheld":null,"homepage":"https://newsela.com/data/","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/problems-in-current-text-simplification","title":"Problems in Current Text Simplification Research: New Data Can Help","first_author":"Wei Xu","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Simplification","url":"/task/text-simplification","datasets_with_task":"/datasets/task/text-simplification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Newsela"],"data_loaders":[],"num_papers_in_archive":106,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-simplification-on-newsela","task":"Text Simplification","dataset_variant":"Newsela","rows":13,"metrics":["SARI","BLEU"],"first_row_in_archive_order":{"model":"CRF Alignment + Transformer","paper":"/paper/neural-crf-model-for-sentence-alignment-in","metrics":{"SARI":"36.6"},"code_links":[{"title":"chaojiang06/wiki-auto","url":"https://github.com/chaojiang06/wiki-auto"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/iterative-edit-based-unsupervised-sentence","title":"Iterative Edit-Based Unsupervised Sentence Simplification","date":"2020-06-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-crf-model-for-sentence-alignment-in","title":"Neural CRF Model for Sentence Alignment in Text Simplification","date":"2020-05-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/editnts-an-neural-programmer-interpreter","title":"EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing","date":"2019-06-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/complexity-weighted-loss-and-diverse","title":"Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification","date":"2019-04-04","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/integrating-transformer-and-paraphrase-rules","title":"Integrating Transformer and Paraphrase Rules for Sentence Simplification","date":"2018-10-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dynamic-multi-level-multi-task-learning-for","title":"Dynamic Multi-Level Multi-Task Learning for Sentence Simplification","date":"2018-06-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sentence-simplification-with-memory-augmented","title":"Sentence Simplification with Memory-Augmented Neural Networks","date":"2018-04-20","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-how-to-simplify-from-explicit","title":"Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs","date":"2017-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sentence-simplification-with-deep","title":"Sentence Simplification with Deep Reinforcement Learning","date":"2017-03-31","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hybrid-simplification-using-deep-semantics","title":"Hybrid Simplification using Deep Semantics and Machine Translation","date":"2014-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sentence-simplification-by-monolingual","title":"Sentence Simplification by Monolingual Machine Translation","date":"2012-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":1,"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."}