{
    "scope": "published-public-metadata",
    "resource": {
        "id": "AISLI-R-118292325452820E9D7F",
        "kind": "dataset",
        "title": "Multi Token Completion",
        "summary": "This dataset provides masked sentences and multi-token phrases that were masked-out of these sentences. We offer 3 datasets: a general purpose dataset extracted from the Wikipedia and Books corpora, and 2 additional datasets extracted from pubmed abstracts. As for the pubmed data, please be aware that the dataset does not reflect the most current/accurate data available from NLM (it is not being updated). For these datasets, the columns provided for each datapoint are as follows: text- the original sentence span- the span (phrase) which is masked out span_lower- the lowercase version of span range- the range in the text string which will be m",
        "provider": "[Amazon](https://www.amazon.com/)",
        "source": "registry.opendata.aws",
        "url": "https://registry.opendata.aws/multi-token-completion/",
        "topics": "科技与开放工具",
        "languages": "",
        "date": "",
        "rights": "Datasets are published under [CC-NC-SA-3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/). Human evaluation is published under [CC-SA-4.0](https://creativecommons.org/licenses/by-sa/4.0/).",
        "access": "metadata_public",
        "state": "metadata",
        "summary_status": "source_metadata",
        "link_status": "source_link",
        "classification_basis": "原目录资源类型"
    },
    "record_url": "https://aiedchair.bnu.edu.cn/resources/?lang=ar&record=AISLI-R-118292325452820E9D7F"
}
