Dataset Open Access

Catalan United Nations v1.0 test set

Marta R. Costa-jussà


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/b9f7fe0c-ed53-47cb-a16d-8e8150da87ab/UN_test_ca.txt"
      }, 
      "checksum": "md5:71dfb8ec7ea6a2bdb4615083f2eb3b71", 
      "bucket": "b9f7fe0c-ed53-47cb-a16d-8e8150da87ab", 
      "key": "UN_test_ca.txt", 
      "type": "txt", 
      "size": 820376
    }
  ], 
  "owners": [
    106850
  ], 
  "doi": "10.5281/zenodo.3888414", 
  "stats": {
    "version_unique_downloads": 9.0, 
    "unique_views": 38.0, 
    "views": 40.0, 
    "version_views": 40.0, 
    "unique_downloads": 9.0, 
    "version_unique_views": 38.0, 
    "volume": 8203760.0, 
    "version_downloads": 10.0, 
    "downloads": 10.0, 
    "version_volume": 8203760.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3888414", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3888413", 
    "bucket": "https://zenodo.org/api/files/b9f7fe0c-ed53-47cb-a16d-8e8150da87ab", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3888413.svg", 
    "html": "https://zenodo.org/record/3888414", 
    "latest_html": "https://zenodo.org/record/3888414", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3888414.svg", 
    "latest": "https://zenodo.org/api/records/3888414"
  }, 
  "conceptdoi": "10.5281/zenodo.3888413", 
  "created": "2020-06-10T16:01:23.499250+00:00", 
  "updated": "2020-06-10T22:18:20.871000+00:00", 
  "conceptrecid": "3888413", 
  "revision": 2, 
  "id": 3888414, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3888414", 
    "description": "<p>Catalan version [1] of the test set from the United Nations v1.0 [2]. The translation was performed in two steps: we did a first automatic translation from the Spanish test set version into Catalan and then a professional translator post-edited the output.</p>\n\n<p><br>\n[1] Marta R. Costa-Juss&agrave;, No&eacute; Casas, Carlos Escolano, and Jos&eacute; A. R. Fonollosa. 2019. Chinese-Catalan: A Neural Machine Translation Approach Based on Pivoting and Attention Mechanisms. <em>ACM Trans. Asian Low-Resour. Lang. Inf. Process.</em> 18, 4, Article 43 (August 2019), 8 pages. DOI:https://doi.org/10.1145/3312575</p>\n\n<p>[2] Michal Ziemski, Marcin Junczys-Dowmunt, and Bruno Pouliquen. 2016. The United Nations parallel corpus v1.0. In<br>\nProceedings of the LREC, 2016</p>", 
    "language": "cat", 
    "title": "Catalan United Nations v1.0 test set", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "journal": {
      "volume": "18", 
      "issue": "4", 
      "title": "ACM Transactions on Asian and Low-Resource Language Information Processing"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3888413"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3888414"
          }
        }
      ]
    }, 
    "access_right": "open", 
    "references": [
      "Costa-juss\u00e0, M.R., Casas, N., Escolano, C. and Fonollosa, J.A.R., Chinese-Catalan: A Neural Machine Translation Approach based on Pivoting and Attention Mechanisms, ACM Transactions on Asian and Low-Resource Language Information Processing, Vol 18, No 4, Art. 43, 2019", 
      "Michal Ziemski, Marcin Junczys-Dowmunt, and Bruno Pouliquen. 2016. The United Nations parallel corpus v1.0. In Proceedings of the LREC, 2016"
    ], 
    "keywords": [
      "Multilingual Parallel Data", 
      "Benchmark", 
      "Catalan", 
      "United Nations"
    ], 
    "publication_date": "2020-06-10", 
    "creators": [
      {
        "orcid": "0000-0002-5703-520X", 
        "affiliation": "Universitat Polit\u00e8cnica de Catalunya", 
        "name": "Marta R. Costa-juss\u00e0"
      }
    ], 
    "notes": "This work is supported by the Spanish Ministerio de Econom\u00eda y Competitividad and European Regional Development\nFund, through the postdoctoral senior grant Ram\u00f3n y Cajal.", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.1145/3312575", 
        "relation": "isCompiledBy", 
        "resource_type": "publication-article"
      }, 
      {
        "scheme": "url", 
        "identifier": "https://www.aclweb.org/anthology/L16-1561", 
        "relation": "cites", 
        "resource_type": "publication-conferencepaper"
      }, 
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3888413", 
        "relation": "isVersionOf"
      }
    ]
  }
}
40
10
views
downloads
All versions This version
Views 4040
Downloads 1010
Data volume 8.2 MB8.2 MB
Unique views 3838
Unique downloads 99

Share

Cite as