{
 "id": "maikezu/nutshell",
 "owner": "maikezu",
 "name": "nutshell",
 "downloads": 1109,
 "likes": 3,
 "last_modified": "2026-05-20T06:26:37.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{zufle-etal-2025-nutshell,\n    title = \"{NUTSHELL}: A Dataset for Abstract Generation from Scientific Talks\",\n    author = {Z{\\\"u}fle, Maike  and\n      Papi, Sara  and\n      Savoldi, Beatrice  and\n      Gaido, Marco  and\n      Bentivogli, Luisa  and\n      Niehues, Jan},\n    editor = \"Salesky, Elizabeth  and\n      Federico, Marcello  and\n      Anastasopoulos, Antonis\",\n    booktitle = \"Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)\",\n    month = jul,\n    year = \"2025\",\n    address = \"Vienna, Austria (in-person and online)\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.iwslt-1.2/\",\n    doi = \"10.18653/v1/2025.iwslt-1.2\",\n    pages = \"19--32\",\n    ISBN = \"979-8-89176-272-5\",\n    abstract = \"Scientific communication is receiving increasing attention in natural language processing, especially to help researches access, summarize, and generate content. One emerging application in this area is Speech-to-Abstract Generation (SAG), which aims to automatically generate abstracts from recorded scientific presentations. SAG enables researchers to efficiently engage with conference talks, but progress has been limited by a lack of large-scale datasets. To address this gap, we introduce NUTSHELL, a novel multimodal dataset of *ACL conference talks paired with their corresponding abstracts. We establish strong baselines for SAG and evaluate the quality of generated abstracts ",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "e8c5a0bd76088c5070509dd76bd41b2eeae5168e",
 "stated_evidence": "https://huggingface.co/datasets/maikezu/nutshell/blob/e8c5a0bd76088c5070509dd76bd41b2eeae5168e/README.md",
 "file_evidence": "https://huggingface.co/datasets/maikezu/nutshell/tree/e8c5a0bd76088c5070509dd76bd41b2eeae5168e",
 "card_nc": false
}