{
    "identifier": "ark:\/88434\/mds2-2161",
    "accessLevel": "public",
    "contactPoint": {
        "hasEmail": "mailto:[email protected]",
        "fn": "Alden A. Dima"
    },
    "programCode": [
        "006:045"
    ],
    "landingPage": "https:\/\/data.nist.gov\/od\/id\/mds2-2161",
    "title": "Training and Test-Related Data for Keyphrase Extraction for Technical Language Processing",
    "description": "Training and test-related data to accompany \"Keyphrase Extraction for Technical Language Processing\" by Alden Dima and Aaron Massey (in press). The subdirectories \"keyphrase-extraction-jct-train\" and \"keyphrase-extraction-jct-test\" contain a total of 1153 ThermoML files which are each associated with a corresponding Journal of Chemical Thermodynamics (JCT) article. These ThermoML files contain information about these papers in extensible markup language (XML) format including the title, authors, abstract, digital object identifier (DOI) and keywords. They also contain thermophysical property data unrelated to the keyphrase extraction study. These files were obtained from the National Institute of Standard and Technology (NIST) Thermodynamics Research Center (TRC) in Boulder, Colorado (https:\/\/trc.nist.gov\/). Readers wishing to replicate this work will also need to obtain the original JCT articles which can be obtained from https:\/\/www.sciencedirect.com\/journal\/the-journal-of-chemical-thermodynamics.",
    "language": [
        "en"
    ],
    "distribution": [
        {
            "accessURL": "https:\/\/doi.org\/10.18434\/M32161",
            "title": "DOI Access for Training and Test-Related Data for Keyphrase Extraction for Scientific Registries"
        },
        {
            "downloadURL": "https:\/\/data.nist.gov\/od\/ds\/mds2-2161\/keyphrase-extraction-jct-data-20191212.tgz.sha256",
            "mediaType": "text\/plain",
            "title": "Hash File for Training and Test-Related Data for Keyphrase Extraction for Scientific Registries"
        },
        {
            "downloadURL": "https:\/\/data.nist.gov\/od\/ds\/mds2-2161\/keyphrase-extraction-jct-data-20191212.tgz",
            "format": ".tgz file of data",
            "description": "Download link for data",
            "mediaType": "application\/gzip",
            "title": "Training and Test-Related Data for Keyphrase Extraction for Scientific Registries"
        }
    ],
    "bureauCode": [
        "006:55"
    ],
    "modified": "2019-12-12 00:00:00",
    "publisher": {
        "@type": "org:Organization",
        "name": "National Institute of Standards and Technology"
    },
    "theme": [
        "Information Technology:Software research",
        "Information Technology:Data and informatics"
    ],
    "keyword": [
        "MGI informatics"
    ]
}