{"url":"/dataset/one-billion-word-benchmark","name":"One Billion Word Benchmark","full_name":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","description_markdown":"Text corpus with almost one billion words of training data for statistical language modeling benchmarking.\r\nThe scale of approximately one billion words attempts to strike a balance between the relevance of the benchmark in a world of abundant data against the ease with which researchers can evaluate their modeling approaches. Monolingual english data was obtained from the WMT11 website and prepared using a variety of best-practices for machine learning dataset preparations.","description_withheld":null,"homepage":"https://github.com/ciprian-chelba/1-billion-word-language-modeling-benchmark","introduced_date":"2013-12-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/one-billion-word-benchmark-for-measuring","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","first_author":"Ciprian Chelba","url":null},"license":{"name":"Apache 2.0","url":"https://github.com/ciprian-chelba/1-billion-word-language-modeling-benchmark/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["One Billion Word Benchmark"],"data_loaders":[],"num_papers_in_archive":66,"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."}