{"url":"/dataset/slurp","name":"SLURP","full_name":"Spoken Language Understanding Resource Package","description_markdown":"A new challenging dataset in English spanning 18 domains, which is substantially bigger and linguistically more diverse than existing datasets.\r\n\r\nSource: [SLURP: A Spoken Language Understanding Resource Package](/paper/slurp-a-spoken-language-understanding-1)","description_withheld":null,"homepage":"https://github.com/pswietojanski/slurp","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/slurp-a-spoken-language-understanding-1","title":"SLURP: A Spoken Language Understanding Resource Package","first_author":"Emanuele Bastianelli","url":null},"license":null,"modalities":[],"tasks":[{"name":"Slot Filling","url":"/task/slot-filling","datasets_with_task":"/datasets/task/slot-filling"},{"name":"Spoken Language Understanding","url":"/task/spoken-language-understanding","datasets_with_task":"/datasets/task/spoken-language-understanding"},{"name":"Intent Classification","url":"/task/intent-classification","datasets_with_task":"/datasets/task/intent-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SLURP"],"data_loaders":[{"repo":"https://github.com/pswietojanski/slurp","url":"https://github.com/pswietojanski/slurp","frameworks":[]}],"num_papers_in_archive":106,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/intent-classification-on-slurp","task":"Intent Classification","dataset_variant":"SLURP","rows":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"TDT 0-8","paper":"/paper/efficient-sequence-transduction-by-jointly","metrics":{"Accuracy (%)":"90.07"},"code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"chimechallenge/C8DASR-Baseline-NeMo","url":"https://github.com/chimechallenge/C8DASR-Baseline-NeMo"},{"title":"kehanlu/Nemo","url":"https://github.com/kehanlu/Nemo"},{"title":"wd929/NeMo","url":"https://github.com/wd929/NeMo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/slot-filling-on-slurp","task":"Slot Filling","dataset_variant":"SLURP","rows":5,"metrics":["F1"],"first_row_in_archive_order":{"model":"TDT 0-6","paper":"/paper/efficient-sequence-transduction-by-jointly","metrics":{"F1":"0.8061"},"code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"chimechallenge/C8DASR-Baseline-NeMo","url":"https://github.com/chimechallenge/C8DASR-Baseline-NeMo"},{"title":"kehanlu/Nemo","url":"https://github.com/kehanlu/Nemo"},{"title":"wd929/NeMo","url":"https://github.com/wd929/NeMo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/efficient-sequence-transduction-by-jointly","title":"Efficient Sequence Transduction by Jointly Predicting Tokens and Durations","date":"2023-04-13","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/finstreder-simple-and-fast-spoken-language","title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","date":"2022-06-29","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/a-fine-tuned-wav2vec-2-0-hubert-benchmark-for","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","date":"2021-11-04","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/slurp-a-spoken-language-understanding-1","title":"SLURP: A Spoken Language Understanding Resource Package","date":"2020-11-26","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":1,"samples_unverified":1,"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."}