{
 "id": "PierreColombo/miam",
 "owner": "PierreColombo",
 "name": "miam",
 "downloads": 419,
 "likes": 11,
 "last_modified": "2024-01-18T11:09:00.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask",
  "text-classification"
 ],
 "citation": "@inproceedings{colombo-etal-2021-code,\n    title = \"Code-switched inspired losses for spoken dialog representations\",\n    author = \"Colombo, Pierre  and\n      Chapuis, Emile  and\n      Labeau, Matthieu  and\n      Clavel, Chlo{\\'e}\",\n    booktitle = \"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2021\",\n    address = \"Online and Punta Cana, Dominican Republic\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2021.emnlp-main.656\",\n    doi = \"10.18653/v1/2021.emnlp-main.656\",\n    pages = \"8320--8337\",\n    abstract = \"Spoken dialogue systems need to be able to handle both multiple languages and multilinguality inside a conversation (\\textit{e.g} in case of code-switching). In this work, we introduce new pretraining losses tailored to learn generic multilingual spoken dialogue representations. The goal of these losses is to expose the model to code-switched language. In order to scale up training, we automatically build a pretraining corpus composed of multilingual conversations in five different languages (French, Italian, English, German and Spanish) from OpenSubtitles, a huge multilingual corpus composed of 24.3G tokens. We test the generic representations on MIAM, a new benchmark composed of five dialogue act corpora on the same aforementioned languages as well as on two novel multilingual tasks (\\textit{i.e} multilingual mask utterance retrieval and multilin",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "f138dd789c15a3b25eee181a4dc4d330741c4c39",
 "stated_evidence": "https://huggingface.co/datasets/PierreColombo/miam/blob/f138dd789c15a3b25eee181a4dc4d330741c4c39/README.md",
 "file_evidence": "https://huggingface.co/datasets/PierreColombo/miam/tree/f138dd789c15a3b25eee181a4dc4d330741c4c39",
 "card_nc": false
}