Conference paper Open Access

Generic and Specialized Word Embeddings for Multi-Domain Machine Translation

Pham, MinhQuang; Crego, Josep; Yvon, François; Senellart, Jean


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>Pham, MinhQuang</dc:creator>
  <dc:creator>Crego, Josep</dc:creator>
  <dc:creator>Yvon, François</dc:creator>
  <dc:creator>Senellart, Jean</dc:creator>
  <dc:date>2019-11-02</dc:date>
  <dc:description>Supervised machine translation works well when the train and test data are sampled from the same distribution. When this is not the case, adaptation techniques help ensure that the knowledge learned from out-of-domain texts generalises to in-domain sentences. We study here a related setting, multi-domain adaptation, where the number of domains is potentially large and adapting separately to each domain would waste training resources. Our proposal transposes to neural machine translation the feature expansion technique of (Daumé III, 2007): it isolates domain-agnostic from domain-specific lexical representations, while sharing the most of the network across domains. Our experiments use two architectures and two language pairs: they show that our approach, while simple and computationally inexpensive, outperforms several strong baselines and delivers a multi-domain system that successfully translates texts from diverse sources.</dc:description>
  <dc:identifier>https://zenodo.org/record/3524979</dc:identifier>
  <dc:identifier>10.5281/zenodo.3524979</dc:identifier>
  <dc:identifier>oai:zenodo.org:3524979</dc:identifier>
  <dc:relation>doi:10.5281/zenodo.3524978</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>Generic and Specialized Word Embeddings for Multi-Domain Machine Translation</dc:title>
  <dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
  <dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>
100
71
views
downloads
All versions This version
Views 100100
Downloads 7171
Data volume 23.9 MB23.9 MB
Unique views 8686
Unique downloads 6464

Share

Cite as