{"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/unsupervised-neural-text-simplification","title":"Unsupervised Neural Text Simplification","arxiv_id":"1810.07931","date":"2018-10-18","proceeding":"ACL 2019 7","authors":["Sai Surya","Abhijit Mishra","Anirban Laha","Parag Jain","Karthik Sankaranarayanan"],"abstract":"The paper presents a first attempt towards unsupervised neural text simplification that relies only on unlabeled text corpora. The core framework is composed of a shared encoder and a pair of attentional-decoders and gains knowledge of simplification through discrimination based-losses and denoising. The framework is trained using unlabeled text collected from en-Wikipedia dump. Our analysis (both quantitative and qualitative involving human evaluators) on a public test data shows that the proposed model can perform text-simplification at both lexical and syntactic levels, competitive to existing supervised methods. Addition of a few labelled pairs also improves the performance further.","url_abs":"https://arxiv.org/abs/1810.07931v6","url_pdf":"https://arxiv.org/pdf/1810.07931v6.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":[{"paper_slug":"unsupervised-neural-text-simplification","repo_url":"https://github.com/subramanyamdvss/UnsupNTS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"text-simplification","task_name":"Text Simplification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-simplification-on-asset","task":"Text Simplification","dataset":"ASSET","model":"UNTS (Unsupervised)","rank_in_archive_order":9,"of":12,"metrics":{"BLEU":"76.14*","SARI (EASSE>=0.2.1)":"35.19"},"uses_additional_data":false},{"leaderboard":"/sota/text-simplification-on-turkcorpus","task":"Text Simplification","dataset":"TurkCorpus","model":"UNMT (Unsupervised)","rank_in_archive_order":15,"of":25,"metrics":{"BLEU":"74.02","SARI (EASSE>=0.2.1)":"37.20"},"uses_additional_data":false},{"leaderboard":"/sota/text-simplification-on-turkcorpus","task":"Text Simplification","dataset":"TurkCorpus","model":"UNTS-10k (Weakly supervised)","rank_in_archive_order":16,"of":25,"metrics":{"SARI (EASSE>=0.2.1)":"37.15"},"uses_additional_data":false},{"leaderboard":"/sota/text-simplification-on-turkcorpus","task":"Text Simplification","dataset":"TurkCorpus","model":"UNTS (Unsupervised)","rank_in_archive_order":20,"of":25,"metrics":{"SARI (EASSE>=0.2.1)":"36.29"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.07931","atlas_url":"https://app.syntology.ai/?focus=1810.07931","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}