{"url":"/dataset/klexikon","name":"Klexikon","full_name":"Klexikon: A German Dataset for Joint Summarization and Simplification","description_markdown":"The dataset introduces document alignments between [German Wikipedia](de.wikipedia.org) and the children's lexicon [Klexikon](klexikon.zum.de).\r\nThe source texts in Wikipedia are both written in a more complex language than Klexikon, and also significantly longer, which makes this a suitable application for both summarization and simplification.\r\nIn fact, previous research has so far only focused on *either* of the two, but not comprehensively been studied as a joint task.","description_withheld":null,"homepage":"https://github.com/dennlinger/klexikon","introduced_date":"2022-01-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/klexikon-a-german-dataset-for-joint","title":"Klexikon: A German Dataset for Joint Summarization and Simplification","first_author":"Dennis Aumiller","url":null},"license":{"name":"CC-BY-SA","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Text Simplification","url":"/task/text-simplification","datasets_with_task":"/datasets/task/text-simplification"}],"languages":[{"name":"German","url":"/datasets/language/german"}],"variants":["Klexikon"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/dennlinger/klexikon","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-klexikon","task":"Text Summarization","dataset_variant":"Klexikon","rows":4,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"Luhn's algorithm (25 sentences)","paper":"/paper/klexikon-a-german-dataset-for-joint","metrics":{"ROUGE-1":"32.00","ROUGE-2":"5.63","ROUGE-L":"11.68"},"code_links":[{"title":"dennlinger/klexikon","url":"https://github.com/dennlinger/klexikon"},{"title":"dennlinger/summaries","url":"https://github.com/dennlinger/summaries"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/klexikon-a-german-dataset-for-joint","title":"Klexikon: A German Dataset for Joint Summarization and Simplification","date":"2022-01-18","rows_on_this_dataset":4,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}