{"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/klexikon-a-german-dataset-for-joint","title":"Klexikon: A German Dataset for Joint Summarization and Simplification","arxiv_id":"2201.07198","date":"2022-01-18","proceeding":"LREC 2022 6","authors":["Dennis Aumiller","Michael Gertz"],"abstract":"Traditionally, Text Simplification is treated as a monolingual translation task where sentences between source texts and their simplified counterparts are aligned for training. However, especially for longer input documents, summarizing the text (or dropping less relevant content altogether) plays an important role in the simplification process, which is currently not reflected in existing datasets. Simultaneously, resources for non-English languages are scarce in general and prohibitive for training new solutions. To tackle this problem, we pose core requirements for a system that can jointly summarize and simplify long source documents. We further describe the creation of a new dataset for joint Text Simplification and Summarization based on German Wikipedia and the German children's lexicon \"Klexikon\", consisting of almost 2900 documents. We release a document-aligned version that particularly highlights the summarization aspect, and provide statistical evidence that this resource is well suited to simplification as well. Code and data are available on Github: https://github.com/dennlinger/klexikon","url_abs":"https://arxiv.org/abs/2201.07198v2","url_pdf":"https://arxiv.org/pdf/2201.07198v2.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":"klexikon-a-german-dataset-for-joint","repo_url":"https://github.com/dennlinger/klexikon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"klexikon-a-german-dataset-for-joint","repo_url":"https://github.com/dennlinger/summaries","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"text-simplification","task_name":"Text Simplification"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[{"slug":"klexikon","name":"Klexikon","full_name":"Klexikon: A German Dataset for Joint Summarization and Simplification"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-summarization-on-klexikon","task":"Text Summarization","dataset":"Klexikon","model":"Luhn's algorithm (25 sentences)","rank_in_archive_order":1,"of":4,"metrics":{"ROUGE-1":"32.00","ROUGE-2":"5.63","ROUGE-L":"11.68"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-klexikon","task":"Text Summarization","dataset":"Klexikon","model":"Lead-k","rank_in_archive_order":2,"of":4,"metrics":{"ROUGE-1":"25.00","ROUGE-2":"5.16","ROUGE-L":"12.10"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-klexikon","task":"Text Summarization","dataset":"Klexikon","model":"Lead-3","rank_in_archive_order":3,"of":4,"metrics":{"ROUGE-1":"17.50","ROUGE-2":"3.94","ROUGE-L":"9.99"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-klexikon","task":"Text Summarization","dataset":"Klexikon","model":"Full article","rank_in_archive_order":4,"of":4,"metrics":{"ROUGE-1":"16.98","ROUGE-2":"4.30","ROUGE-L":"7.09"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.07198","atlas_url":"https://app.syntology.ai/?focus=2201.07198","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}