{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/wikiatomicedits-a-multilingual-corpus-of","title":"WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse","arxiv_id":"1808.09422","date":"2018-08-28","proceeding":"EMNLP 2018 10","authors":["Manaal Faruqui","Ellie Pavlick","Ian Tenney","Dipanjan Das"],"abstract":"We release a corpus of 43 million atomic edits across 8 languages. These\nedits are mined from Wikipedia edit history and consist of instances in which a\nhuman editor has inserted a single contiguous phrase into, or deleted a single\ncontiguous phrase from, an existing sentence. We use the collected data to show\nthat the language generated during editing differs from the language that we\nobserve in standard corpora, and that models trained on edits encode different\naspects of semantics and discourse than models trained on raw, unstructured\ntext. We release the full corpus as a resource to aid ongoing research in\nsemantics, discourse, and representation learning.","url_abs":"http://arxiv.org/abs/1808.09422v1","url_pdf":"http://arxiv.org/pdf/1808.09422v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"wikiatomicedits","name":"WikiAtomicEdits","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.09422","atlas_url":"https://app.syntology.ai/?focus=1808.09422","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}