February 12, 2021 Journal article Open Access

MinhQuang Pham; Josep Crego; François Yvon

JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from un-expected domains in testing. This multi-domain scenario has attracted a lot of recent work, that fall under the general umbrella of transfer learning. In this study, we revisit multi-domain machine translation, with the aim to formulate the motivations for developing such systems and the associated expectations with respect to performance. Our experiments with a large sample of multi-domain systems show that most of these expectations are hardly met and suggest that further work is needed to better analyze the current behaviour of multi-domain systems and to make them fully hold their promises.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "SYSTRAN, LIMSI/CNRS", 
      "@type": "Person", 
      "name": "MinhQuang Pham"
    }, 
    {
      "affiliation": "SYSTRAN", 
      "@type": "Person", 
      "name": "Josep Crego"
    }, 
    {
      "affiliation": "LIMSI/CNRS", 
      "@type": "Person", 
      "name": "Fran\u00e7ois Yvon"
    }
  ], 
  "headline": "Revisiting Multi-Domain Machine Translation", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2021-02-12", 
  "url": "https://zenodo.org/record/4537184", 
  "keywords": [
    "Neural Machine Translation", 
    "Multi-domain MT", 
    "Domain Adaptation"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.4537184", 
  "@id": "https://doi.org/10.5281/zenodo.4537184", 
  "@type": "ScholarlyArticle", 
  "name": "Revisiting Multi-Domain Machine Translation"
}