{
 "id": "eusip/silicone",
 "owner": "eusip",
 "name": "silicone",
 "downloads": 514,
 "likes": 13,
 "last_modified": "2024-01-18T11:15:53.000Z",
 "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{chapuis-etal-2020-hierarchical,\n    title = \"Hierarchical Pre-training for Sequence Labelling in Spoken Dialog\",\n    author = \"Chapuis, Emile  and\n      Colombo, Pierre  and\n      Manica, Matteo  and\n      Labeau, Matthieu  and\n      Clavel, Chlo{\\'e}\",\n    booktitle = \"Findings of the Association for Computational Linguistics: EMNLP 2020\",\n    month = nov,\n    year = \"2020\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://www.aclweb.org/anthology/2020.findings-emnlp.239\",\n    doi = \"10.18653/v1/2020.findings-emnlp.239\",\n    pages = \"2636--2648\",\n    abstract = \"Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate on a new benchmark we call Sequence labellIng evaLuatIon benChmark fOr spoken laNguagE benchmark (SILICONE). SILICONE is model-agnostic and contains 10 different datasets of various sizes. We obtain our representations with a hierarchical encoder based on transformer architectures, for which we extend two well-known pre-training objectives. Pre-training is performed on OpenSubtitles: a large corpus of spoken dialog containing over 2.3 billion of tokens. We demonstrate how hierarchical encoders achieve competitive results with consistently fewer parameters compared to state-of-the-art models and we show their imp",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "f9e4b166dced70ccc4ddca59ad5e894b5d822b79",
 "stated_evidence": "https://huggingface.co/datasets/eusip/silicone/blob/f9e4b166dced70ccc4ddca59ad5e894b5d822b79/README.md",
 "file_evidence": "https://huggingface.co/datasets/eusip/silicone/tree/f9e4b166dced70ccc4ddca59ad5e894b5d822b79",
 "card_nc": false
}