Conference paper Open Access

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

Philipp Wiesenbach; Stefan Riezler


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Philipp Wiesenbach</dc:creator>
  <dc:creator>Stefan Riezler</dc:creator>
  <dc:date>2019-11-02</dc:date>
  <dc:description>Machine translation of ancient languages faces a low-resource problem, caused by the limited amount of available textual source data and their translations. We present a multi-task modeling approach to translating Middle Egyptian that is inspired by recent successful approaches to multi-task learning in end-to-end speech translation. We leverage the phonographic aspect of the hieroglyphic writing system, and show that similar to multi-task learning of speech recognition and translation, joint learning and sharing of structural information between hieroglyph transcriptions, translations, and POS tagging can improve direct translation of hieroglyphs by several BLEU points, using a minimal amount of manual transcriptions.</dc:description>
  <dc:identifier>https://zenodo.org/record/3524924</dc:identifier>
  <dc:identifier>10.5281/zenodo.3524924</dc:identifier>
  <dc:identifier>oai:zenodo.org:3524924</dc:identifier>
  <dc:language>eng</dc:language>
  <dc:relation>doi:10.5281/zenodo.3524923</dc:relation>
  <dc:relation>url:https://zenodo.org/communities/iwslt2019</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:title>Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs</dc:title>
  <dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
  <dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>
69
42
views
downloads
All versions This version
Views 6969
Downloads 4242
Data volume 6.0 MB6.0 MB
Unique views 6060
Unique downloads 4141

Share

Cite as