There is a newer version of this record available.

Dataset Open Access

Webis Query Spelling Corpus 2017 (Webis-QSpell-17)

Hagen, Matthias; Potthast, Martin; Stein, Benno; Gohsen, Marcel; Rathgeber, Anja


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/3eb4baff-3b2b-42dc-98f2-75e3af86bd9a/corpus-webis-qspell-17.zip"
      }, 
      "checksum": "md5:cda2d9bf28ff94a2f17dc97a642b8b84", 
      "bucket": "3eb4baff-3b2b-42dc-98f2-75e3af86bd9a", 
      "key": "corpus-webis-qspell-17.zip", 
      "type": "zip", 
      "size": 1073998
    }
  ], 
  "owners": [
    65747
  ], 
  "doi": "10.5281/zenodo.3256201", 
  "stats": {
    "version_unique_downloads": 61.0, 
    "unique_views": 200.0, 
    "views": 212.0, 
    "version_views": 268.0, 
    "unique_downloads": 41.0, 
    "version_unique_views": 236.0, 
    "volume": 52625902.0, 
    "version_downloads": 76.0, 
    "downloads": 49.0, 
    "version_volume": 114339937.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3256201", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3256200", 
    "bucket": "https://zenodo.org/api/files/3eb4baff-3b2b-42dc-98f2-75e3af86bd9a", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3256200.svg", 
    "html": "https://zenodo.org/record/3256201", 
    "latest_html": "https://zenodo.org/record/3570912", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3256201.svg", 
    "latest": "https://zenodo.org/api/records/3570912"
  }, 
  "conceptdoi": "10.5281/zenodo.3256200", 
  "created": "2019-06-26T09:41:28.742362+00:00", 
  "updated": "2020-01-24T19:22:25.193207+00:00", 
  "conceptrecid": "3256200", 
  "revision": 8, 
  "id": 3256201, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3256201", 
    "description": "<p>The Webis Query Spelling Corpus 2017 (Webis-QSpell-17) contains 54,772 web queries that were manually spell-checked; for 9,171 queries alternative spelling variants are contained.</p>\n\n<p>As for segmentations of many of the queries (i.e., tagged concepts and phrases), please refer to the companion corpus <a href=\"https://webis.de/data/webis-qsec-10.html\">Webis-QSeC-10</a>.</p>", 
    "language": "eng", 
    "title": "Webis Query Spelling Corpus 2017 (Webis-QSpell-17)", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 2, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3256200"
          }, 
          "is_last": false, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3570912"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "webis"
      }
    ], 
    "references": [
      "Matthias Hagen, Martin Potthast, Marcel Gohsen, Anja Rathgeber, and Benno Stein. A Large-Scale Query Spelling Correction Corpus. In Noriko Kando et al, editors, 40th International ACM Conference on Research and Development in Information Retrieval (SIGIR 2017), pages 1261-1264, August 2017. ACM. ISBN 978-1-4503-5022-8."
    ], 
    "keywords": [
      "queries", 
      "AOL", 
      "spelling", 
      "dictionaries", 
      "search engines"
    ], 
    "publication_date": "2017-08-11", 
    "creators": [
      {
        "orcid": "0000-0002-9733-2890", 
        "affiliation": "Bauhaus-Universit\u00e4t Weimar", 
        "name": "Hagen, Matthias"
      }, 
      {
        "orcid": "0000-0003-2451-0665", 
        "affiliation": "Bauhaus-Universit\u00e4t Weimar", 
        "name": "Potthast, Martin"
      }, 
      {
        "orcid": "0000-0001-9033-2217", 
        "affiliation": "Bauhaus-Universit\u00e4t Weimar", 
        "name": "Stein, Benno"
      }, 
      {
        "affiliation": "Bauhaus-Universit\u00e4t Weimar", 
        "name": "Gohsen, Marcel"
      }, 
      {
        "affiliation": "Bauhaus-Universit\u00e4t Weimar", 
        "name": "Rathgeber, Anja"
      }
    ], 
    "meeting": {
      "acronym": "SIGIR 2017", 
      "title": "40th International ACM Conference on Research and Development in Information Retrieval"
    }, 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3256200", 
        "relation": "isVersionOf"
      }
    ]
  }
}
268
76
views
downloads
All versions This version
Views 268212
Downloads 7649
Data volume 114.3 MB52.6 MB
Unique views 236200
Unique downloads 6141

Share

Cite as