Lexical Micro-adaptation for Neural Machine Translation - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Lexical Micro-adaptation for Neural Machine Translation

Jitao Xu
  • Function : Author
  • PersonId : 184998
  • IdHAL : xujitao
Josep Crego
  • Function : Author
Jean Senellart
  • Function : Author
  • PersonId : 1038145

Abstract

This work is inspired by a typical machine translation industry scenario in which translators make use of in-domain data for facilitating translation of similar or repeating sentences. We introduce a generic framework applied at inference in which a subset of segment pairs are first extracted from training data according to their similarity to the input sentences. These segments are then used to dynamically update the parameters of a generic NMT network, thus performing a lexical micro-adaptation. Our approach demonstrates strong adaptation performance to new and existing datasets including pseudo in-domain data. We evaluate our approach on a heterogeneous English-French training dataset showing accuracy gains on all evaluated domains when compared to strong adaptation baselines.
Fichier principal
Vignette du fichier
IWSLT2019_paper_9.pdf (422.2 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02635039 , version 1 (27-05-2020)

Identifiers

  • HAL Id : hal-02635039 , version 1

Cite

Jitao Xu, Josep Crego, Jean Senellart. Lexical Micro-adaptation for Neural Machine Translation. International Workshop on Spoken Language Translation, Nov 2019, Hong Kong, Hong Kong SAR China. ⟨hal-02635039⟩
101 View
66 Download

Share

Gmail Facebook X LinkedIn More