{
 "id": "GEM/SciDuet",
 "owner": "GEM",
 "name": "SciDuet",
 "downloads": 333,
 "likes": 4,
 "last_modified": "2022-10-24T15:30:06.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "other"
 ],
 "citation": "@inproceedings{sun-etal-2021-d2s,\n    title = \"{D}2{S}: Document-to-Slide Generation Via Query-Based Text Summarization\",\n    author = \"Sun, Edward  and\n      Hou, Yufang  and\n      Wang, Dakuo  and\n      Zhang, Yunfeng  and\n      Wang, Nancy X. R.\",\n    booktitle = \"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies\",\n    month = jun,\n    year = \"2021\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2021.naacl-main.111\",\n    doi = \"10.18653/v1/2021.naacl-main.111\",\n    pages = \"1405--1418\",\n    abstract = \"Presentations are critical for communication in all areas of our lives, yet the creation of slide decks is often tedious and time-consuming. There has been limited research aiming to automate the document-to-slides generation process and all face a critical challenge: no publicly available dataset for training and benchmarking. In this work, we first contribute a new dataset, SciDuet, consisting of pairs of papers and their corresponding slides decks from recent years{'} NLP and ML conferences (e.g., ACL). Secondly, we present D2S, a novel system that tackles the document-to-slides task with a two-step approach: 1) Use slide titles to retrieve relevant and engaging text, figures, and tables; 2) Summarize the retrieved context into bullet points with long-form question answering. Our evaluation suggests that lo",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "23c4a628af8312f25fe40efcc094d6502d1198e8",
 "stated_evidence": "https://huggingface.co/datasets/GEM/SciDuet/blob/23c4a628af8312f25fe40efcc094d6502d1198e8/README.md",
 "file_evidence": "https://huggingface.co/datasets/GEM/SciDuet/tree/23c4a628af8312f25fe40efcc094d6502d1198e8",
 "card_nc": false
}