publication . Conference object . 2020

Integrating Domain Terminology into Neural Machine Translation

Elise Michon; Josep Crego; Jean Senellart;
Open Access English
  • Published: 08 Dec 2020
  • Publisher: International Committee on Computational Linguistics
Abstract
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 ...
Persistent Identifiers
Subjects
free text keywords: Neural Machine Translation, Terminology, Domain Adaptation
Funded by
EC| ANITA
Project
ANITA
Advanced tools for fighting oNline Illegal TrAfficking
  • Funder: European Commission (EC)
  • Project Code: 787061
  • Funding stream: H2020 | RIA
Any information missing or wrong?Report an Issue