{"url":"/dataset/ibm-debater-mention-detection-benchmark","name":"IBM Debater Mention Detection Benchmark","full_name":null,"description_markdown":"This dataset contains general and named entities annotations on both clean written text and on noisy speech data. \r\nIt includes 1000 sentences from Wikipedia and 1000 sentences of speech data that appear in two forms: (1) transcribed manually, and (2) the output of an ASR engine. \r\nEach of the datasets includes a total of around 6500 mentions linked to there DBPedia pages.","description_withheld":null,"homepage":"https://www.research.ibm.com/haifa/dept/vst/debating_data.shtml","introduced_date":"2018-01-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/what-did-you-mention-a-large-scale-mention","title":"What did you Mention? A Large Scale Mention Detection Benchmark for Spoken and Written Text","first_author":"Yosi Mass","url":null},"license":{"name":"CC BY-SA 3.0","url":"http://creativecommons.org/licenses/by-sa/3.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["IBM Debater Mention Detection Benchmark"],"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."}