Journal article Open Access

Revisiting Multi-Domain Machine Translation

MinhQuang Pham; Josep Crego; François Yvon


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.4537184", 
  "container_title": "Transactions of the Association for Computational Linguistics", 
  "language": "eng", 
  "title": "Revisiting Multi-Domain Machine Translation", 
  "issued": {
    "date-parts": [
      [
        2021, 
        2, 
        12
      ]
    ]
  }, 
  "abstract": "<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>", 
  "author": [
    {
      "family": "MinhQuang Pham"
    }, 
    {
      "family": "Josep Crego"
    }, 
    {
      "family": "Fran\u00e7ois Yvon"
    }
  ], 
  "volume": "9", 
  "type": "article-journal", 
  "id": "4537184"
}
42
25
views
downloads
All versions This version
Views 4242
Downloads 2525
Data volume 7.1 MB7.1 MB
Unique views 2929
Unique downloads 2323

Share

Cite as