{"url":"/dataset/celex","name":"CELEX","full_name":"CELEX","description_markdown":"**CELEX** database comprises three different searchable lexical databases, Dutch, English and German. The lexical data contained in each database is divided into five categories: orthography, phonology, morphology, syntax (word class) and word frequency.\r\n\r\nSource: [Polysemy and Brevity versus Frequency in Language](https://arxiv.org/abs/1904.00812)\r\nImage Source: [https://www.aclweb.org/anthology/W17-7619.pdf](https://www.aclweb.org/anthology/W17-7619.pdf)","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC96L14","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"The CELEX lexical database","first_author":null,"url":"https://catalog.ldc.upenn.edu/LDC96L14"},"license":{"name":"Custom (research-only)","url":"https://catalog.ldc.upenn.edu/license/celex-user-agreement.pdf"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"},{"name":"Morphological Analysis","url":"/task/morphological-analysis","datasets_with_task":"/datasets/task/morphological-analysis"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"German","url":"/datasets/language/german"},{"name":"Dutch","url":"/datasets/language/dutch"}],"variants":["CELEX"],"data_loaders":[],"num_papers_in_archive":59,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}