{"url":"/dataset/dream","name":"DREAM","full_name":null,"description_markdown":"DREAM is a multiple-choice Dialogue-based REAding comprehension exaMination dataset. In contrast to existing reading comprehension datasets, DREAM is the first to focus on in-depth multi-turn multi-party dialogue understanding.\r\n\r\nDREAM contains 10,197 multiple choice questions for 6,444 dialogues, collected from English-as-a-foreign-language examinations designed by human experts. DREAM is likely to present significant challenges for existing reading comprehension systems: 84% of answers are non-extractive, 85% of questions require reasoning beyond a single sentence, and 34% of questions also involve commonsense knowledge.\r\n\r\nSource: [DREAM](https://dataset.org/dream/)","description_withheld":null,"homepage":"https://dataset.org/dream/","introduced_date":"2019-03-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/dream-a-challenge-data-set-and-models-for","title":"DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension","first_author":"Kai Sun","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"https://github.com/nlpdata/dream/blob/master/license.txt"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Machine Reading Comprehension","url":"/task/machine-reading-comprehension","datasets_with_task":"/datasets/task/machine-reading-comprehension"},{"name":"Sleep spindles detection","url":"/task/sleep-spindles-detection","datasets_with_task":"/datasets/task/sleep-spindles-detection"}],"languages":[],"variants":["DREAMS sleep spindles","DREAM"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/dataset-org/dream","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/dream","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#dream","frameworks":["pytorch"]}],"num_papers_in_archive":68,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/machine-reading-comprehension-on-dream","task":"Machine Reading Comprehension","dataset_variant":"DREAM","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ASA + RoBERTa","paper":"/paper/adversarial-self-attention-for-language","metrics":{"Accuracy":"69.2"},"code_links":[{"title":"gingasan/adversarialsa","url":"https://github.com/gingasan/adversarialsa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sleep-spindles-detection-on-dreams-sleep","task":"Sleep spindles detection","dataset_variant":"DREAMS sleep spindles","rows":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"Robust autoregressive hidden semi-Markov model","paper":"/paper/robust-autoregressive-hidden-semi-markov","metrics":{"MCC":"0.455"},"code_links":[{"title":"carlosloza/DNDBN","url":"https://github.com/carlosloza/DNDBN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/instructive-dialogue-summarization-with-query","title":"Instructive Dialogue Summarization with Query Aggregations","date":"2023-10-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adversarial-self-attention-for-language","title":"Adversarial Self-Attention for Language Understanding","date":"2022-06-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/robust-autoregressive-hidden-semi-markov","title":"Deep Neural Dynamic Bayesian Networks applied to EEG sleep spindles modeling","date":"2020-10-16","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}