{"url":"/dataset/hinglish-top","name":"Hinglish-TOP","full_name":null,"description_markdown":"**Hinglish-TOP** is a human annotated code-switched semantic parsing dataset containing 10k human annotations for Hindi-English (HINGLISH) code switched utterances, and over 170K CST5 generated code-switched utterances from the TOPv2 dataset.\r\n\r\nSource: [CST5: Data Augmentation for Code-Switched Semantic Parsing](https://arxiv.org/pdf/2211.07514v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.07514v1.pdf](https://arxiv.org/pdf/2211.07514v1.pdf)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/hinglish-top-dataset","introduced_date":"2022-11-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/cst5-data-augmentation-for-code-switched-1","title":"CST5: Data Augmentation for Code-Switched Semantic Parsing","first_author":"Anmol Agarwal","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/google-research-datasets/Hinglish-TOP-Dataset/blob/main/LICENSE.md"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Semantic Parsing","url":"/task/semantic-parsing","datasets_with_task":"/datasets/task/semantic-parsing"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Hindi","url":"/datasets/language/hindi"}],"variants":["Hinglish-TOP"],"data_loaders":[{"repo":"https://github.com/vavinash992/portofolio_website","url":"https://github.com/vavinash992/portofolio_website","frameworks":["tf"]}],"num_papers_in_archive":1,"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."}