November 12, 2020 Dataset Open Access

Irina Nikishina; Alexander Panchenko; Varvara Logacheva; Natalia Loukachevitch

JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/ea41c56d-dca1-4a07-8b8a-6e77857da5b8/datasets.zip"
      }, 
      "checksum": "md5:cc053dc6fd255044c0085c0c52ed8086", 
      "bucket": "ea41c56d-dca1-4a07-8b8a-6e77857da5b8", 
      "key": "datasets.zip", 
      "type": "zip", 
      "size": 1248958
    }
  ], 
  "owners": [
    89559
  ], 
  "doi": "10.5281/zenodo.4279821", 
  "stats": {
    "version_unique_downloads": 22.0, 
    "unique_views": 107.0, 
    "views": 132.0, 
    "version_views": 177.0, 
    "unique_downloads": 17.0, 
    "version_unique_views": 129.0, 
    "volume": 21232286.0, 
    "version_downloads": 22.0, 
    "downloads": 17.0, 
    "version_volume": 23823081.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.4279821", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.4270477", 
    "bucket": "https://zenodo.org/api/files/ea41c56d-dca1-4a07-8b8a-6e77857da5b8", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.4270477.svg", 
    "html": "https://zenodo.org/record/4279821", 
    "latest_html": "https://zenodo.org/record/4279821", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.4279821.svg", 
    "latest": "https://zenodo.org/api/records/4279821"
  }, 
  "conceptdoi": "10.5281/zenodo.4270477", 
  "created": "2020-11-18T20:24:51.765179+00:00", 
  "updated": "2020-11-19T00:27:05.789262+00:00", 
  "conceptrecid": "4270477", 
  "revision": 3, 
  "id": 4279821, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.4279821", 
    "description": "<p>We choose two versions of WordNet and then select words which appear only in a newer version. For each word, we get its hypernyms from the newer WordNet version and consider them as gold standard hypernyms. We add words to the dataset if only their hypernyms appear in both snippets. We do not consider adjectives and adverbs, because they often introduce abstract concepts and are difficult to interpret by context.</p>\n\n<p>Previous dataset (RUSSE&#39;2020) does not include short words (&lt;4&nbsp;symbols), diminutives, named entities and other constraints described in the shared task paper. We remove those constraints and present a non-restricted Russian dataset and a symmetrical English dataset from WordNet database.</p>", 
    "language": "rus", 
    "title": "Studying Taxonomy Enrichment on Diachronic WordNet Versions", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 2, 
          "index": 1, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "4270477"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "4279821"
          }
        }
      ]
    }, 
    "keywords": [
      "RuWordNet, wordnets"
    ], 
    "publication_date": "2020-11-12", 
    "creators": [
      {
        "orcid": "0000-0003-4910-8568", 
        "affiliation": "Skolkovo Institute of Science and Technology, Moscow, Russia", 
        "name": "Irina Nikishina"
      }, 
      {
        "affiliation": "Skolkovo Institute of Science and Technology, Moscow, Russia", 
        "name": "Alexander Panchenko"
      }, 
      {
        "affiliation": "Skolkovo Institute of Science and Technology, Moscow, Russia", 
        "name": "Varvara Logacheva"
      }, 
      {
        "affiliation": "Research Computing Center, Lomonosov Moscow State University, Moscow, Russia", 
        "name": "Natalia Loukachevitch"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.4270477", 
        "relation": "isVersionOf"
      }
    ]
  }
}