Dataset Open Access

Webis Abstractive Snippet Corpus 2020

Chen ,Wei-Fan; Syed, Shahbaz; Potthast, Martin; Hagen, Matthias; Stein, Benno


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/6d79d6cb-fcb6-4fdf-81f6-61fa005123cb/released-snippet-ac-qb.zip"
      }, 
      "checksum": "md5:41696d93df837a53f871c0e402eb0a22", 
      "bucket": "6d79d6cb-fcb6-4fdf-81f6-61fa005123cb", 
      "key": "released-snippet-ac-qb.zip", 
      "type": "zip", 
      "size": 4252964846
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/6d79d6cb-fcb6-4fdf-81f6-61fa005123cb/released-snippet-ac.zip"
      }, 
      "checksum": "md5:f36a9c50a117d5bee91831b4a23c7bb0", 
      "bucket": "6d79d6cb-fcb6-4fdf-81f6-61fa005123cb", 
      "key": "released-snippet-ac.zip", 
      "type": "zip", 
      "size": 6631607911
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/6d79d6cb-fcb6-4fdf-81f6-61fa005123cb/released-snippet-dmoz-qb.zip"
      }, 
      "checksum": "md5:ed30087f82080000ac5e67b23a8d8c98", 
      "bucket": "6d79d6cb-fcb6-4fdf-81f6-61fa005123cb", 
      "key": "released-snippet-dmoz-qb.zip", 
      "type": "zip", 
      "size": 23224318
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/6d79d6cb-fcb6-4fdf-81f6-61fa005123cb/released-snippet-dmoz.zip"
      }, 
      "checksum": "md5:511694a7c9e4794364eaff89838e0039", 
      "bucket": "6d79d6cb-fcb6-4fdf-81f6-61fa005123cb", 
      "key": "released-snippet-dmoz.zip", 
      "type": "zip", 
      "size": 244438672
    }
  ], 
  "owners": [
    65747
  ], 
  "doi": "10.5281/zenodo.3653834", 
  "stats": {
    "version_unique_downloads": 363.0, 
    "unique_views": 732.0, 
    "views": 817.0, 
    "version_views": 817.0, 
    "unique_downloads": 363.0, 
    "version_unique_views": 732.0, 
    "volume": 10818013338785.0, 
    "version_downloads": 2694.0, 
    "downloads": 2694.0, 
    "version_volume": 10818013338785.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3653834", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3653833", 
    "bucket": "https://zenodo.org/api/files/6d79d6cb-fcb6-4fdf-81f6-61fa005123cb", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3653833.svg", 
    "html": "https://zenodo.org/record/3653834", 
    "latest_html": "https://zenodo.org/record/3653834", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3653834.svg", 
    "latest": "https://zenodo.org/api/records/3653834"
  }, 
  "conceptdoi": "10.5281/zenodo.3653833", 
  "created": "2020-02-07T11:32:58.049494+00:00", 
  "updated": "2020-03-02T15:10:41.334479+00:00", 
  "conceptrecid": "3653833", 
  "revision": 10, 
  "id": 3653834, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3653834", 
    "description": "<p>The Webis Abstractive Snippet 2020 (Webis-Snippete-20) comprises four abstractive snippet dataset from ClueWeb09, Clueweb12, and DMOZ descriptions. More than 10 million &lt;webpage, abstractive snippet&gt; pairs / 3.5 million &lt;query, webpage, abstractive snippet&gt; pairs were collected.</p>", 
    "language": "eng", 
    "title": "Webis Abstractive Snippet Corpus 2020", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3653833"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3653834"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "webis"
      }
    ], 
    "keywords": [
      "abstractive snippet"
    ], 
    "publication_date": "2020-02-07", 
    "creators": [
      {
        "orcid": "0000-0003-3400-6075", 
        "affiliation": "Paderborn University", 
        "name": "Chen ,Wei-Fan"
      }, 
      {
        "affiliation": "Leipzig University", 
        "name": "Syed, Shahbaz"
      }, 
      {
        "orcid": "0000-0003-2451-0665", 
        "affiliation": "Leipzig University", 
        "name": "Potthast, Martin"
      }, 
      {
        "orcid": "0000-0002-9733-2890", 
        "affiliation": "Martin-Luther-Universit\u00e4t Halle-Wittenberg", 
        "name": "Hagen, Matthias"
      }, 
      {
        "orcid": "0000-0001-9033-2217", 
        "affiliation": "Bauhaus-Universit\u00e4t Weimar", 
        "name": "Stein, Benno"
      }
    ], 
    "meeting": {
      "acronym": "WWW20", 
      "dates": "20-24 April, 2020", 
      "place": "Taipei, Taiwan", 
      "title": "The Web Conference 2020"
    }, 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3653833", 
        "relation": "isVersionOf"
      }
    ]
  }
}
817
2,694
views
downloads
All versions This version
Views 817817
Downloads 2,6942,694
Data volume 10.8 TB10.8 TB
Unique views 732732
Unique downloads 363363

Share

Cite as