{"url":"/dataset/pcc","name":"PCC","full_name":"Potsdam Commentary Corpus","description_markdown":"The Potsdam Commentary Corpus (PCC) is a corpus of 220 German newspaper commentaries (2.900 sentences, 44.000 tokens) taken from the online issues of the Märkische Allgemeine Zeitung (MAZ subcorpus) and Tagesspiegel (ProCon subcorpus) and is annotated with a range of different types of linguistic information.\r\n\r\nThe central subcorpus that we are making publicly available consists of 176 MAZ texts, which are annotated with\r\n\r\n* Sentence Syntax\r\n* Coreference\r\n* Discourse Structure (RST & PDTB)\r\n* Aboutness topics","description_withheld":null,"homepage":"http://angcl.ling.uni-potsdam.de/resources/pcc.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons Attribution-NonCommercial-ShareAlike","url":null},"modalities":[],"tasks":[{"name":"Constituency Parsing","url":"/task/constituency-parsing","datasets_with_task":"/datasets/task/constituency-parsing"},{"name":"Discourse Parsing","url":"/task/discourse-parsing","datasets_with_task":"/datasets/task/discourse-parsing"}],"languages":[{"name":"German","url":"/datasets/language/german"}],"variants":["PCC"],"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."}