Generic and Specialized Word Embeddings for Multi-Domain Machine Translation - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Generic and Specialized Word Embeddings for Multi-Domain Machine Translation

Minh Quang Pham
Josep-Maria Crego
  • Function : Author
  • PersonId : 1038144
François Yvon
Jean Senellart
  • Function : Author
  • PersonId : 1038145

Abstract

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 (Daum\'e 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.
Fichier principal
Vignette du fichier
IWSLT2019_paper_10.pdf (328.18 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02343215 , version 1 (02-11-2019)

Identifiers

Cite

Minh Quang Pham, Josep-Maria Crego, François Yvon, Jean Senellart. Generic and Specialized Word Embeddings for Multi-Domain Machine Translation. International Workshop on Spoken Language Translation, Nov 2019, Hong-Kong, China. ⟨10.5281/zenodo.3524978⟩. ⟨hal-02343215⟩
637 View
265 Download

Altmetric

Share

Gmail Facebook X LinkedIn More