{"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/multi-word-lexical-simplification","title":"Multi-Word Lexical Simplification","arxiv_id":null,"date":"2020-12-01","proceeding":"COLING 2020 8","authors":["Piotr Przyby{\\l}a","Matthew Shardlow"],"abstract":"In this work we propose the task of multi-word lexical simplification, in which a sentence in natural language is made easier to understand by replacing its fragment with a simpler alternative, both of which can consist of many words. In order to explore this new direction, we contribute a corpus (MWLS1), including 1462 sentences in English from various sources with 7059 simplifications provided by human annotators. We also propose an automatic solution (Plainifier) based on a purpose-trained neural language model and evaluate its performance, comparing to human and resource-based baselines.","url_abs":"https://aclanthology.org/2020.coling-main.123","url_pdf":"https://aclanthology.org/2020.coling-main.123.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":"multi-word-lexical-simplification","repo_url":"https://github.com/piotrmp/mwls1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"multi-word-lexical-simplification","repo_url":"https://github.com/piotrmp/plainifier","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"multi-word-lexical-simplification","repo_url":"https://github.com/piotrmp/tersebert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"lexical-simplification","task_name":"Lexical Simplification"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}