Conference paper Open Access

Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs

Philipp Wiesenbach; Stefan Riezler


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3524924", 
  "language": "eng", 
  "title": "Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs", 
  "issued": {
    "date-parts": [
      [
        2019, 
        11, 
        2
      ]
    ]
  }, 
  "abstract": "<p>Machine translation of ancient languages faces a low-resource problem, caused by the limited amount of available textual source data&nbsp;and their translations. We present a multi-task modeling approach to translating Middle Egyptian that is inspired by recent successful&nbsp;approaches to multi-task learning in end-to-end speech translation. We leverage the phonographic aspect of the hieroglyphic writing&nbsp;system, and show that similar to multi-task learning of speech recognition and translation, joint learning and sharing of structural&nbsp;information between hieroglyph transcriptions, translations, and POS tagging can improve direct translation of hieroglyphs by several&nbsp;BLEU points, using a minimal amount of manual transcriptions.</p>", 
  "author": [
    {
      "family": "Philipp Wiesenbach"
    }, 
    {
      "family": "Stefan Riezler"
    }
  ], 
  "type": "paper-conference", 
  "id": "3524924"
}
66
42
views
downloads
All versions This version
Views 6666
Downloads 4242
Data volume 6.0 MB6.0 MB
Unique views 5959
Unique downloads 4141

Share

Cite as