{"url":"/dataset/twitter-pos-vcb","name":"Twitter PoS VCB","full_name":"Twitter part-of-speech vote-constrained-bootstrapping","description_markdown":"The data is about 1.5 million English tweets annotated for part-of-speech using Ritter's extension of the PTB tagset. The tweets are from 2012 and 2013, tokenized using the GATE tokenizer and tagged jointly using the CMU ARK tagger and Ritter's T-POS tagger. Only when both these taggers' outputs are completely compatible over a whole tweet, is that tweet added to the dataset.","description_withheld":null,"homepage":"https://gate.ac.uk/wiki/twitter-postagger.html","introduced_date":"2013-09-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/twitter-part-of-speech-tagging-for-all","title":"Twitter Part-of-Speech Tagging for All: Overcoming Sparse and Noisy Data","first_author":"Leon Derczynski","url":null},"license":{"name":"CC-BY 4.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Twitter PoS VCB"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/strombergnlp/twitter_pos_vcb","frameworks":["tf","pytorch","jax"]}],"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."}