{"url":"/dataset/big-bird","name":"BiRD","full_name":"Bigram Relatedness Dataset","description_markdown":"**Bigram Relatedness Dataset** (**BiRD**) is a large, fine-grained, bigram relatedness dataset, using a comparative annotation technique called Best Worst Scaling. Each of BiRD's 3,345 English term pairs involves at least one bigram. BiRD is made freely available to foster further research on how meaning can be represented and how meaning can be composed.\r\n\r\nImage source: [http://saifmohammad.com/WebPages/BiRD.html](http://saifmohammad.com/WebPages/BiRD.html)","description_withheld":null,"homepage":"http://saifmohammad.com/WebPages/BiRD.html","introduced_date":"2019-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/big-bird-a-large-fine-grained-bigram","title":"Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition","first_author":"Shima Asaadi","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["BiRD"],"data_loaders":[],"num_papers_in_archive":10,"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."}