Evaluating Domain Adaptation for Machine Translation Across Scenarios

Authors: Thierry Etchegoyhen Anna Fernández Torné Andoni Azpeitia Zaldua Anna Matamala

Date: 23.01.2019


Abstract

We present an evaluation of the benefits of domain adaptation for machine translation, on three separate domains and language pairs, with varying degrees of domain specificity and amounts of available training data. Domain-adapted statistical and neural machine translation systems are compared to each other and to generic online systems, thus providing an evaluation of the main options in terms of machine translation. Alongside automated translation metrics, we present experimental results involving professional translators, in terms of quality assessment, subjective evaluations of the task and post-editing productivity measurements. The results we present quantify the clear advantages of domain adaptation for machine translation, with marked impacts for domains with higher specificity. Additionally, the results of the experiments show domain-adapted neural machine translation systems to be the optimal choice overall.

BIB_text

@Article {
title = {Evaluating Domain Adaptation for Machine Translation Across Scenarios},
pages = {6-15},
keywds = {
Machine Translation, Domain Adaptation, Quality Evaluation, Productivity Evaluation, Subjective Evaluation
}
abstract = {

We present an evaluation of the benefits of domain adaptation for machine translation, on three separate domains and language pairs, with varying degrees of domain specificity and amounts of available training data. Domain-adapted statistical and neural machine translation systems are compared to each other and to generic online systems, thus providing an evaluation of the main options in terms of machine translation. Alongside automated translation metrics, we present experimental results involving professional translators, in terms of quality assessment, subjective evaluations of the task and post-editing productivity measurements. The results we present quantify the clear advantages of domain adaptation for machine translation, with marked impacts for domains with higher specificity. Additionally, the results of the experiments show domain-adapted neural machine translation systems to be the optimal choice overall.


}
isbn = {979-10-95546-00-9},
date = {2019-01-23},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (Spain)

+(34) 943 309 230

close overlay