{"url":"/dataset/break","name":"BREAK","full_name":"BREAK","description_markdown":"Break is a question understanding dataset, aimed at training models to reason over complex questions. It features 83,978 natural language questions, annotated with a new meaning representation, Question Decomposition Meaning Representation (QDMR). Each example has the natural question along with its QDMR representation. Break contains human composed questions, sampled from 10 leading question-answering benchmarks over text, images and databases. This dataset was created by a team of NLP researchers at Tel Aviv University and Allen Institute for AI.\r\n\r\nSource: [BREAK](https://allenai.github.io/Break/)","description_withheld":null,"homepage":"https://allenai.github.io/Break/","introduced_date":"2020-01-31","introduced_date_note":null,"introduced_by":{"paper":"/paper/break-it-down-a-question-understanding","title":"Break It Down: A Question Understanding Benchmark","first_author":"Tomer Wolfson","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","datasets_with_task":"/datasets/task/open-domain-question-answering"}],"languages":[],"variants":["BREAK"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/break_data","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/break_data","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":39,"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."}