Metadonnées au format TEI

 
<?xml version="1.0" encoding="utf-8"?>
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>Europarl3</title>  
        <author>Jörg Tiedemann</author>
      </titleStmt>
      <publicationStmt><publisher/>
        <availability>
            <p>Téléchargement</p>
            <p>http://opus.lingfil.uu.se/Europarl3.php</p>
        </availability>
      </publicationStmt>
      <sourceDesc>
        <p>web (Parlement Européen)</p>
      </sourceDesc>
      <profileDesc>
        <langUsage>
          <language>Danish, Greek, English, Spanish, Finnish, French, Italian, Dutch, Polish, Portuguese, Slovak</language>
        </langUsage>
      </profileDesc>
      <encodingDesc>
        <projectDesc>
           <p>Corpus parallèle issu du site du Parlement Européen. Environ 40 millions de mots par langue, 11 langues (da, de, el, en, es, fi, fr, it, nl, pt, sv).

11 languages, 55 bitexts (3.5 G)
total number of files: 7,034
total number of tokens: 404.01M
total number of sentence fragments: 15.81M</p>
          <p>traduction automatique, machine learning</p>
        </projectDesc>
      </encodingDesc>
    </fileDesc>
  </teiHeader>