{"url":"/dataset/spmrl-hebrew-segmentation-data","name":"SPMRL Hebrew segmentation data","full_name":null,"description_markdown":"Training data for Hebrew morphological word segmentation","description_withheld":null,"homepage":"https://github.com/amir-zeldes/RFTokenizer/","introduced_date":"2014-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/introducing-the-spmrl-2014-shared-task-on","title":"Introducing the SPMRL 2014 Shared Task on Parsing Morphologically-rich Languages","first_author":"Djam{\\'e} Seddah","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Segmentation","url":"/task/text-segmentation","datasets_with_task":"/datasets/task/text-segmentation"}],"languages":[{"name":"Hebrew","url":"/datasets/language/hebrew"}],"variants":["SPMRL Hebrew segmentation data"],"data_loaders":[],"num_papers_in_archive":2,"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."}