{"url":"/dataset/conll-2017-shared-task-automatically","name":"CoNLL 2017 Shared Task - Automatically Annotated Raw Texts and Word Embeddings","full_name":null,"description_markdown":"Automatic segmentation, tokenization and morphological and syntactic annotations of raw texts in 45 languages, generated by UDPipe (http://ufal.mff.cuni.cz/udpipe), together with word embeddings of dimension 100 computed from lowercased texts by word2vec (https://code.google.com/archive/p/word2vec/).","description_withheld":null,"homepage":"http://hdl.handle.net/11234/1-1989","introduced_date":"2017-03-15","introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"},{"name":"Sequential sentence segmentation","url":"/task/sequential-sentence-segmentation","datasets_with_task":"/datasets/task/sequential-sentence-segmentation"},{"name":"Text Segmentation","url":"/task/text-segmentation","datasets_with_task":"/datasets/task/text-segmentation"},{"name":"Sentence segmentation","url":"/task/sentence-segmentation","datasets_with_task":"/datasets/task/sentence-segmentation"},{"name":"Morphological Tagging","url":"/task/morphological-tagging","datasets_with_task":"/datasets/task/morphological-tagging"}],"languages":[{"name":"Multilingual","url":"/datasets/language/multilingual"}],"variants":["CoNLL 2017 Shared Task - Automatically Annotated Raw Texts and Word Embeddings"],"data_loaders":[],"num_papers_in_archive":1,"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."}