{
  "_schema": "https://data.nist.gov/od/dm/nerdm-schema/v0.7#",
  "@context": [
    "https://data.nist.gov/od/dm/nerdm-pub-context.jsonld",
    {
      "@base": "ark:/88434/mds2-3168"
    }
  ],
  "@type": [
    "nrdp:DataPublication",
    "nrdp:PublicDataResource",
    "dcat:Dataset"
  ],
  "_extensionSchemas": [
    "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/PublicDataResource"
  ],
  "@id": "ark:/88434/mds2-3168",
  "ediid": "ark:/88434/mds2-3168",
  "version": "1.0.0",
  "doi": "doi:10.18434/mds2-3168",
  "title": "ChemNLP: A Natural Language-Processing-Based Library for Materials Chemistry Text Data",
  "contactPoint": {
    "fn": "Daniel Wines",
    "hasEmail": "mailto:daniel.wines@nist.gov"
  },
  "modified": "2024-02-07",
  "status": "available",
  "landingPage": "https://data.nist.gov/od/id/mds2-3168",
  "description": [
    "We present the ChemNLP library that can be used for (1) curating open access datasets for materials and chemistry literature, developing and comparing traditional machine learning, transformers and graph neural network models for (2) classifying and clustering texts, (3) named entity recognition for large-scale text-mining, (4) abstractive summarization for generating titles of articles from abstracts, (5) text generation for suggesting abstracts from titles, (6) integration with density functional theory dataset for identifying potential candidate materials such as superconductors, and (7) web-interface development for text and reference query. We primarily use the publicly available arXiv and PubChem datasets, but the tools can be used for other datasets as well. Moreover, as new models are developed, they can be easily integrated in the library"
  ],
  "keyword": [
    "Algorithms",
    "Materials",
    "Materials science",
    "Mathematical methods",
    "Superconductors",
    "NLP",
    "LLM"
  ],
  "topic": [
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Chemistry: Theoretical chemistry and modeling"
    },
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Materials: Superconductors"
    },
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Physics: Condensed matter"
    },
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Materials: Modeling and computational material science"
    }
  ],
  "references": [
    {
      "@type": [
        "npg:Document"
      ],
      "@id": "#ref:10.1021/acs.jpcc.3c03106",
      "refType": "IsSupplementTo",
      "location": "https://doi.org/10.1021/acs.jpcc.3c03106",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/bib/v0.7#/definitions/DCiteReference"
      ],
      "title": "ChemNLP: A Natural Language-Processing-Based Library for Materials Chemistry Text Data",
      "issued": "2023-08-25",
      "citation": "Choudhary, K., & Kelley, M. L. (2023). ChemNLP: A Natural Language-Processing-Based Library for Materials Chemistry Text Data. The Journal of Physical Chemistry C, 127(35), 17545\u00e2\u0080\u009317555. https://doi.org/10.1021/acs.jpcc.3c03106\n"
    }
  ],
  "accessLevel": "public",
  "license": "https://www.nist.gov/open/license",
  "publisher": {
    "name": "National Institute of Standards and Technology",
    "@type": "org:Organization"
  },
  "language": [
    "en"
  ],
  "bureauCode": [
    "006:55"
  ],
  "programCode": [
    "006:052"
  ],
  "components": [
    {
      "accessURL": "https://jarvis.nist.gov/jarvischemnlp/",
      "title": "JARVIS-ChemNLP web",
      "@type": [
        "nrdp:AccessPage",
        "dcat:Distribution"
      ],
      "@id": "#jarvischemnlp/",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/AccessPage"
      ]
    },
    {
      "accessURL": "https://github.com/usnistgov/chemnlp",
      "title": "ChemNLP GitHub",
      "@type": [
        "nrdp:AccessPage",
        "dcat:Distribution"
      ],
      "@id": "#usnistgov/chemnlp",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/AccessPage"
      ]
    }
  ],
  "theme": [
    "Chemistry: Theoretical chemistry and modeling",
    "Materials: Superconductors",
    "Physics: Condensed matter",
    "Materials: Modeling and computational material science"
  ],
  "_editStatus": "done",
  "authors": [
    {
      "familyName": "Choudhary",
      "fn": "Kamal  Choudhary",
      "givenName": "Kamal",
      "middleName": "",
      "affiliation": [
        {
          "title": "National Institute of Standards and Technology",
          "@type": "org:Organization",
          "@id": "ror:05xpvk416"
        }
      ],
      "orcid": "0000-0001-9737-8074",
      "@type": "foaf:Person"
    },
    {
      "familyName": "Kelley",
      "fn": "Mathew L. Kelley",
      "givenName": "Mathew",
      "middleName": "L.",
      "affiliation": [
        {
          "title": "National Institute of Standards and Technology",
          "@type": "org:Organization",
          "@id": "ror:05xpvk416"
        }
      ],
      "orcid": "0000-0002-6940-4148",
      "@type": "foaf:Person"
    }
  ],
  "annotated": "2025-09-25T12:16:31.716240",
  "revised": "2025-09-25T12:16:31.716240",
  "issued": null,
  "firstIssued": "2025-09-25T12:16:31.716240"
}