Dataset Open Access

Palmetto position storing Lucene index of Dutch Wikipedia

van der Zwaan, Janneke M.; Marx, Maarten; Kamps, Jaap


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/e9e57e1b-1c51-4141-beba-a2e9441be923/case_study.pdf"
      }, 
      "checksum": "md5:11b81cdd6ed9520fbc46ada4bf0012b5", 
      "bucket": "e9e57e1b-1c51-4141-beba-a2e9441be923", 
      "key": "case_study.pdf", 
      "type": "pdf", 
      "size": 146622
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e9e57e1b-1c51-4141-beba-a2e9441be923/README.md"
      }, 
      "checksum": "md5:17f782f72275d98e71f4eb901ae26146", 
      "bucket": "e9e57e1b-1c51-4141-beba-a2e9441be923", 
      "key": "README.md", 
      "type": "md", 
      "size": 1777
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/e9e57e1b-1c51-4141-beba-a2e9441be923/nlwiki-palmetto.tar.gz"
      }, 
      "checksum": "md5:c7762b00271203e5fde48816cf1f9f03", 
      "bucket": "e9e57e1b-1c51-4141-beba-a2e9441be923", 
      "key": "nlwiki-palmetto.tar.gz", 
      "type": "gz", 
      "size": 658182830
    }
  ], 
  "owners": [
    20232
  ], 
  "doi": "10.5281/zenodo.46377", 
  "stats": {
    "version_unique_downloads": 43.0, 
    "unique_views": 3642.0, 
    "views": 3656.0, 
    "downloads": 57.0, 
    "unique_downloads": 43.0, 
    "version_unique_views": 3641.0, 
    "volume": 7244438222.0, 
    "version_downloads": 57.0, 
    "version_views": 3655.0, 
    "version_volume": 7244438222.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.46377", 
    "latest_html": "https://zenodo.org/record/46377", 
    "bucket": "https://zenodo.org/api/files/e9e57e1b-1c51-4141-beba-a2e9441be923", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.46377.svg", 
    "html": "https://zenodo.org/record/46377", 
    "latest": "https://zenodo.org/api/records/46377"
  }, 
  "created": "2016-02-23T16:00:47+00:00", 
  "updated": "2019-04-10T03:44:00.166736+00:00", 
  "conceptrecid": "630391", 
  "revision": 9, 
  "id": 46377, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.46377", 
    "description": "<p>Dutch language resource for calculating topic coherence with Palmetto [1, 2]. The dataset is a position storing Lucene index of the Dutch Wikipedia [3]. It was created in the context of the Netherlands eScience Center Dilipad project [4]. The pdf file contains the results of a case study that shows best topic coherence measure for topics consisting of Dutch nouns is NPMI.</p>\n\n<p>More details can be found in the README.</p>\n\n<p>[1] M. Roeder, A. Both, and A. Hinneburg. Exploring the space of topic coherence measures. In <em>Proceedings of the Eighth ACM International Conference on Web Search and Data Mining</em>, pages 399&ndash;408, 2015.</p>\n\n<p>[2] http://aksw.org/Projects/Palmetto.html</p>\n\n<p>[3] https://dumps.wikimedia.org/nlwiki/20151102/</p>\n\n<p>[4] https://www.esciencecenter.nl/project/dilipad</p>", 
    "license": {
      "id": "CC-BY-SA-4.0"
    }, 
    "title": "Palmetto position storing Lucene index of Dutch Wikipedia", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "630391"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "46377"
          }
        }
      ]
    }, 
    "keywords": [
      "topic modeling", 
      "topic coherence", 
      "Palmetto", 
      "Dutch", 
      "Wikipedia"
    ], 
    "publication_date": "2016-02-22", 
    "creators": [
      {
        "affiliation": "Netherlands eScience Center", 
        "name": "van der Zwaan,  Janneke M."
      }, 
      {
        "affiliation": "University of Amsterdam", 
        "name": "Marx, Maarten"
      }, 
      {
        "affiliation": "University of Amsterdam", 
        "name": "Kamps, Jaap"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }
  }
}
3,655
57
views
downloads
All versions This version
Views 3,6553,656
Downloads 5757
Data volume 7.2 GB7.2 GB
Unique views 3,6413,642
Unique downloads 4343

Share

Cite as