{"url":"/dataset/snips","name":"SNIPS","full_name":"SNIPS Natural Language Understanding benchmark","description_markdown":"The **SNIPS** Natural Language Understanding benchmark is a dataset of over 16,000 crowdsourced queries distributed among 7 user intents of various complexity:\r\n\r\n* SearchCreativeWork (e.g. Find me the I, Robot television show),\r\n* GetWeather (e.g. Is it windy in Boston, MA right now?),\r\n* BookRestaurant (e.g. I want to book a highly rated restaurant in Paris tomorrow night),\r\n* PlayMusic (e.g. Play the last track from Beyoncé off Spotify),\r\n* AddToPlaylist (e.g. Add Diamonds to my roadtrip playlist),\r\n* RateBook (e.g. Give 6 stars to Of Mice and Men),\r\n* SearchScreeningEvent (e.g. Check the showtimes for Wonder Woman in Paris).\r\nThe training set contains of 13,084 utterances, the validation set and the test set contain 700 utterances each, with 100 queries per intent.\r\n\r\nSource: [https://paperswithcode.com/paper/snips-voice-platform-an-embedded-spoken/](https://paperswithcode.com/paper/snips-voice-platform-an-embedded-spoken/)","description_withheld":null,"homepage":"https://github.com/sonos/nlu-benchmark","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/snips-voice-platform-an-embedded-spoken","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","first_author":"Alice Coucke","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-learning"},{"name":"Intent Detection","url":"/task/intent-detection","datasets_with_task":"/datasets/task/intent-detection"},{"name":"Slot Filling","url":"/task/slot-filling","datasets_with_task":"/datasets/task/slot-filling"},{"name":"Open Intent Discovery","url":"/task/open-intent-discovery","datasets_with_task":"/datasets/task/open-intent-discovery"},{"name":"Out of Distribution (OOD) Detection","url":"/task/ood-detection","datasets_with_task":"/datasets/task/ood-detection"},{"name":"Intent Discovery","url":"/task/intent-discovery","datasets_with_task":"/datasets/task/intent-discovery"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"}],"variants":["SNIPS"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/sonos-nlu-benchmark/snips_built_in_intents","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/snips_built_in_intents","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/sonos/nlu-benchmark","url":"https://github.com/sonos/nlu-benchmark","frameworks":[]}],"num_papers_in_archive":256,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/intent-detection-on-snips","task":"Intent Detection","dataset_variant":"SNIPS","rows":10,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CTRAN","paper":"/paper/ctran-cnn-transformer-based-network-for","metrics":{"Accuracy":"99.42"},"code_links":[{"title":"rafiepour/CTran","url":"https://github.com/rafiepour/CTran"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/slot-filling-on-snips","task":"Slot Filling","dataset_variant":"SNIPS","rows":10,"metrics":["F1","F1 (1-shot) avg","F1 (5-shot) avg"],"first_row_in_archive_order":{"model":"CTRAN","paper":"/paper/ctran-cnn-transformer-based-network-for","metrics":{"F1":"98.3"},"code_links":[{"title":"rafiepour/CTran","url":"https://github.com/rafiepour/CTran"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-intent-discovery-on-snips","task":"Open Intent Discovery","dataset_variant":"SNIPS","rows":2,"metrics":["ACC","ARI","NMI"],"first_row_in_archive_order":{"model":"DSSCC","paper":"/paper/intent-detection-and-discovery-from-user-logs","metrics":{"ACC":"94.87","ARI":"89.03","NMI":"90.44"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/intent-discovery-on-snips","task":"Intent Discovery","dataset_variant":"SNIPS","rows":1,"metrics":["ARI"],"first_row_in_archive_order":{"model":"k-PCA + HDBSCAN","paper":"/paper/a-hybrid-architecture-for-out-of-domain","metrics":{"ARI":"59.23"},"code_links":[{"title":"Makbari1997/VAE-KPCA-HDBSCAN","url":"https://github.com/Makbari1997/VAE-KPCA-HDBSCAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/out-of-distribution-ood-detection-on-snips","task":"Out of Distribution (OOD) Detection","dataset_variant":"SNIPS","rows":1,"metrics":["F1 Macro"],"first_row_in_archive_order":{"model":"BERT + VAE","paper":"/paper/a-hybrid-architecture-for-out-of-domain","metrics":{"F1 Macro":"92.32"},"code_links":[{"title":"Makbari1997/VAE-KPCA-HDBSCAN","url":"https://github.com/Makbari1997/VAE-KPCA-HDBSCAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-learning-on-snips","task":"Zero-Shot Learning","dataset_variant":"SNIPS","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ZSL-KG","paper":"/paper/zero-shot-learning-with-common-sense","metrics":{"Accuracy":"88.98"},"code_links":[{"title":"BatsResearch/zsl-kg","url":"https://github.com/BatsResearch/zsl-kg"},{"title":"BatsResearch/nayak-arxiv20-code","url":"https://github.com/BatsResearch/nayak-arxiv20-code"},{"title":"batsresearch/nayak-tmlr22-code","url":"https://github.com/batsresearch/nayak-tmlr22-code"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/decomposed-meta-learning-for-few-shot","title":"Decomposed Meta-Learning for Few-Shot Sequence Labeling","date":"2024-03-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ctran-cnn-transformer-based-network-for","title":"CTRAN: CNN-Transformer-based Network for Natural Language Understanding","date":"2023-03-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-hybrid-architecture-for-out-of-domain","title":"A Hybrid Architecture for Out of Domain Intent Detection and Intent Discovery","date":"2023-03-07","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cae-mechanism-to-diminish-the-class","title":"CAE: Mechanism to Diminish the Class Imbalanced in SLU Slot Filling Task","date":"2022-09-21","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/intent-detection-and-discovery-from-user-logs","title":"Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering","date":"2022-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lidsnet-a-lightweight-on-device-intent","title":"LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network","date":"2021-10-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/zero-shot-learning-with-common-sense","title":"Zero-Shot Learning with Common Sense Knowledge Graphs","date":"2020-06-18","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/td-gin-token-level-dynamic-graph-interactive","title":"AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling","date":"2020-04-21","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/discovering-new-intents-via-constrained-deep","title":"Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement","date":"2019-11-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-slot-filling-by-utilizing","title":"Improving Slot Filling by Utilizing Contextual Information","date":"2019-11-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-stack-propagation-framework-with-token","title":"A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding","date":"2019-09-05","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/a-novel-bi-directional-interrelated-model-for","title":"A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling","date":"2019-06-30","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/joint-slot-filling-and-intent-detection-via","title":"Joint Slot Filling and Intent Detection via Capsule Neural Networks","date":"2018-12-22","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/slot-gated-modeling-for-joint-slot-filling","title":"Slot-Gated Modeling for Joint Slot Filling and Intent Prediction","date":"2018-06-01","rows_on_this_dataset":2,"code_links":2,"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."}