November 2, 2019 Conference paper Open Access

Xu, Jitao; Crego, Josep; Senellart, Jean

Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3524977", 
  "language": "eng", 
  "title": "Lexical Micro-adaptation for Neural Machine Translation", 
  "issued": {
    "date-parts": [
      [
        2019, 
        11, 
        2
      ]
    ]
  }, 
  "abstract": "<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>", 
  "author": [
    {
      "family": "Xu, Jitao"
    }, 
    {
      "family": "Crego, Josep"
    }, 
    {
      "family": "Senellart, Jean"
    }
  ], 
  "type": "paper-conference", 
  "id": "3524977"
}