{"url":"/dataset/dl-hard","name":"DL-HARD","full_name":"Deep Learning Hard","description_markdown":"Deep Learning Hard  (**DL-HARD**) is an annotated dataset designed to more effectively evaluate neural ranking models on complex topics. It builds on TREC Deep Learning (DL) questions extensively annotated with query intent categories, answer types, wikified entities, topic categories, and result type metadata from a leading web search engine.\r\n\r\nDL-HARD contains 50 queries from the official 2019/2020 evaluation benchmark, half of which are newly and independently assessed. Overall, DL-HARD is a new resource that promotes research on neural ranking methods by focusing on challenging and complex queries.","description_withheld":null,"homepage":"https://github.com/grill-lab/DL-HARD","introduced_date":"2021-05-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/how-deep-is-your-learning-the-dl-hard","title":"How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset","first_author":"Iain Mackie","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DL-HARD"],"data_loaders":[{"repo":"https://github.com/grill-lab/DL-Hard","url":"https://github.com/grill-lab/DL-HARD","frameworks":[]}],"num_papers_in_archive":9,"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."}