{"url":"/dataset/xsid","name":"xSID","full_name":"Cross-lingual Slot and Intent Detection","description_markdown":"xSID, a new evaluation benchmark for cross-lingual (X) Slot and Intent Detection in 13 languages from 6 language families,  including a very low-resource dialect, covering Arabic (ar), Chinese (zh), Danish (da), Dutch (nl), English (en), German (de), Indonesian (id), Italian (it), Japanese (ja), Kazakh (kk), Serbian (sr), Turkish (tr) and an Austro-Bavarian German dialect, South Tyrolean (de-st).","description_withheld":null,"homepage":"https://bitbucket.org/robvanderg/xsid","introduced_date":"2021-05-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/from-masked-language-modeling-to-translation","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","first_author":"Rob van der Goot","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"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"},{"name":"Zero-Shot Cross-Lingual Transfer","url":"/task/zero-shot-cross-lingual-transfer","datasets_with_task":"/datasets/task/zero-shot-cross-lingual-transfer"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Danish","url":"/datasets/language/danish"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Kazakh","url":"/datasets/language/kazakh"},{"name":"Serbian","url":"/datasets/language/serbian"},{"name":"Turkish","url":"/datasets/language/turkish"}],"variants":["xSID"],"data_loaders":[{"repo":"https://bitbucket.org/robvanderg/xsid","url":"https://bitbucket.org/robvanderg/xsid","frameworks":[]}],"num_papers_in_archive":18,"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."}