{"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/a-new-aligned-simple-german-corpus","title":"A New Aligned Simple German Corpus","arxiv_id":"2209.01106","date":"2022-09-02","proceeding":null,"authors":["Vanessa Toborek","Moritz Busch","Malte Boßert","Christian Bauckhage","Pascal Welke"],"abstract":"\"Leichte Sprache\", the German counterpart to Simple English, is a regulated language aiming to facilitate complex written language that would otherwise stay inaccessible to different groups of people. We present a new sentence-aligned monolingual corpus for Simple German -- German. It contains multiple document-aligned sources which we have aligned using automatic sentence-alignment methods. We evaluate our alignments based on a manually labelled subset of aligned documents. The quality of our sentence alignments, as measured by F1-score, surpasses previous work. We publish the dataset under CC BY-SA and the accompanying code under MIT license.","url_abs":"https://arxiv.org/abs/2209.01106v4","url_pdf":"https://arxiv.org/pdf/2209.01106v4.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":"a-new-aligned-simple-german-corpus","repo_url":"https://github.com/mlai-bonn/simple-german-corpus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.01106","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}