Conference paper Open Access

Lexical Micro-adaptation for Neural Machine Translation

Xu, Jitao; Crego, Josep; Senellart, Jean

JSON-LD ( Export

  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  "description": "<p>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&nbsp;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.</p>", 
  "license": "", 
  "creator": [
      "affiliation": "SYSTRAN, 5 rue Feydeau, 75002 Paris (France)", 
      "@type": "Person", 
      "name": "Xu, Jitao"
      "affiliation": "SYSTRAN, 5 rue Feydeau, 75002 Paris (France)", 
      "@type": "Person", 
      "name": "Crego, Josep"
      "affiliation": "SYSTRAN, 5 rue Feydeau, 75002 Paris (France)", 
      "@type": "Person", 
      "name": "Senellart, Jean"
  "headline": "Lexical Micro-adaptation for Neural Machine Translation", 
  "image": "", 
  "datePublished": "2019-11-02", 
  "url": "", 
  "@context": "", 
  "identifier": "", 
  "@id": "", 
  "@type": "ScholarlyArticle", 
  "name": "Lexical Micro-adaptation for Neural Machine Translation"
All versions This version
Views 129129
Downloads 9999
Data volume 42.8 MB42.8 MB
Unique views 109109
Unique downloads 8686


Cite as