{"url":"/dataset/linked-wikitext-2","name":"Linked WikiText-2","full_name":null,"description_markdown":"The Linked Wikitext-2 language modeling dataset contains over 2 million tokens from Wikipedia articles, along with annotations linking mentions to their corresponding entities and relations in Wikidata. It is designed to match as closely as possible the contents of the popular WikiText-2 dataset.","description_withheld":null,"homepage":"https://rloganiv.github.io/linked-wikitext-2/#/","introduced_date":"2019-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/baracks-wife-hillary-using-knowledge-graphs-1","title":"Barack's Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling","first_author":"Robert Logan","url":null},"license":{"name":"CC-BY-SA-3.0","url":"http://creativecommons.org/licenses/by-sa/3.0/us/"},"modalities":[],"tasks":[{"name":"Data-to-Text Generation","url":"/task/data-to-text-generation","datasets_with_task":"/datasets/task/data-to-text-generation"}],"languages":[],"variants":["Linked WikiText-2"],"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."}