Conference paper Open Access

SIMPITIKI: A Simplification Corpus for Italian

Tonelli, Sara; Palmero Aprosio, Alessio; Saltori, Francesca


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/c9ea90a9-f002-4615-8045-1b9b84222893/clic2016-SIMPITIKI.pdf"
      }, 
      "checksum": "md5:cd5e7c28497a46824e563e377a18dc0d", 
      "bucket": "c9ea90a9-f002-4615-8045-1b9b84222893", 
      "key": "clic2016-SIMPITIKI.pdf", 
      "type": "pdf", 
      "size": 351770
    }
  ], 
  "owners": [
    56329
  ], 
  "doi": "10.5281/zenodo.2534132", 
  "stats": {
    "version_unique_downloads": 71.0, 
    "unique_views": 72.0, 
    "views": 78.0, 
    "version_views": 78.0, 
    "unique_downloads": 71.0, 
    "version_unique_views": 72.0, 
    "volume": 27438060.0, 
    "version_downloads": 78.0, 
    "downloads": 78.0, 
    "version_volume": 27438060.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.2534132", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.2534131", 
    "bucket": "https://zenodo.org/api/files/c9ea90a9-f002-4615-8045-1b9b84222893", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.2534131.svg", 
    "html": "https://zenodo.org/record/2534132", 
    "latest_html": "https://zenodo.org/record/2534132", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.2534132.svg", 
    "latest": "https://zenodo.org/api/records/2534132"
  }, 
  "conceptdoi": "10.5281/zenodo.2534131", 
  "created": "2019-01-08T10:09:18.905764+00:00", 
  "updated": "2020-01-20T13:54:19.507569+00:00", 
  "conceptrecid": "2534131", 
  "revision": 6, 
  "id": 2534132, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.2534132", 
    "version": "2.", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "SIMPITIKI: A Simplification Corpus for Italian", 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.2534131", 
        "relation": "isVersionOf"
      }
    ], 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "2534131"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "2534132"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "692819", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::692819"
        }, 
        "title": "SIMplifying the interaction with Public Administration Through Information technology for Citizens and cOmpanies", 
        "acronym": "SIMPATICO", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "communities": [
      {
        "id": "h2020-simpatico-692819"
      }
    ], 
    "publication_date": "2019-01-08", 
    "creators": [
      {
        "affiliation": "Fondazione Bruno Kessler", 
        "name": "Tonelli, Sara"
      }, 
      {
        "affiliation": "Fondazione Bruno Kessler", 
        "name": "Palmero Aprosio, Alessio"
      }, 
      {
        "affiliation": "Fondazione Bruno Kessler", 
        "name": "Saltori, Francesca"
      }
    ], 
    "meeting": {
      "acronym": "CLIC-it", 
      "dates": "2016", 
      "place": "Naples, Italy", 
      "title": "Third Italian Conference on Computational Linguistics"
    }, 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }, 
    "description": "<p>In this work, we analyse whether&nbsp;Wikipedia can be used to leverage simplification pairs instead of Simple Wikipedia,&nbsp;which has proved unreliable for assessing automatic simplification systems, and&nbsp;is available only in English. We focus&nbsp;on sentence pairs in which the target sentence is the outcome of a Wikipedia edit&nbsp;marked as &lsquo;simplified&rsquo;, and manually annotate simplification phenomena following an existing scheme proposed for previous simplification corpora in Italian.&nbsp;The outcome of this work is the SIMPITIKI corpus, which we make freely available, with pairs of sentences extracted&nbsp;from Wikipedia edits and annotated with&nbsp;simplification types. The resource contains also another corpus with roughly&nbsp;the same number of simplifications, which&nbsp;was manually created by simplifying documents in the administrative domain</p>"
  }
}
78
78
views
downloads
All versions This version
Views 7878
Downloads 7878
Data volume 27.4 MB27.4 MB
Unique views 7272
Unique downloads 7171

Share

Cite as