Conference paper Open Access

Integrating Domain Terminology into Neural Machine Translation

Elise Michon; Josep Crego; Jean Senellart


Citation Style Language JSON Export

{
  "DOI": "10.18653/v1/2020.coling-main.348", 
  "language": "eng", 
  "title": "Integrating Domain Terminology into Neural Machine Translation", 
  "issued": {
    "date-parts": [
      [
        2020, 
        12, 
        8
      ]
    ]
  }, 
  "abstract": "<p>This paper extends existing work on terminology integration into Neural Machine Translation, a common industrial practice to dynamically adapt translation to a specific domain. Our method, based on the use of placeholders complemented with morphosyntactic annotation, efficiently taps into the ability of the neural network to deal with symbolic knowledge to surpass the surface generalization shown by alternative techniques. We compare our approach to state-of-the-art systems and benchmark them through a well-defined evaluation framework, focusing on actual application of terminology and not just on the overall performance. Results indicate the suitability of our method in the use-case where terminology is used in a system trained on generic data only.</p>", 
  "author": [
    {
      "family": "Elise Michon"
    }, 
    {
      "family": "Josep Crego"
    }, 
    {
      "family": "Jean Senellart"
    }
  ], 
  "id": "4537095", 
  "event-place": "Barcelona", 
  "type": "paper-conference", 
  "event": "International Conference on Computational Linguistics (COLING'2020)"
}
38
27
views
downloads
Views 38
Downloads 27
Data volume 7.2 MB
Unique views 27
Unique downloads 26

Share

Cite as