Summary of Survey of Low-Resource Machine Translation

Authors

  • Alexandra Birch University of Edinburgh
  • Barry Haddow University of Edinburgh
  • Rachel Bawden INRIA
  • Jindrich Helcl University of Edinburgh
  • Antonio Valerio Miceli Barone University of Edinburgh

Abstract

We present a summary of a survey covering the state of the art in low resource machine translation. There are currently around 7000 languages spoken in the world and almost all language pairs lack significant resources for training MT models. There has been increasing interest in research addressing the challenge of producing useful translation models when very little translated training data is available. We present a high level summary of this topical field and provide and overview of best practices.

Author Biographies

  • Alexandra Birch, University of Edinburgh
    School of Informatics, Senior Research Fellow
  • Barry Haddow, University of Edinburgh
    School of Informatics, Senior Research Associate
  • Rachel Bawden, INRIA
    Researcher
  • Jindrich Helcl, University of Edinburgh
    Research Associate
  • Antonio Valerio Miceli Barone, University of Edinburgh
    Research Associate

Published

2024-12-05

Issue

Past Publications

Section

Survey article