English

Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation

Computation and Language 2019-06-05 v1 Machine Learning

Abstract

Noise and domain are important aspects of data quality for neural machine translation. Existing research focus separately on domain-data selection, clean-data selection, or their static combination, leaving the dynamic interaction across them not explicitly examined. This paper introduces a "co-curricular learning" method to compose dynamic domain-data selection with dynamic clean-data selection, for transfer learning across both capabilities. We apply an EM-style optimization procedure to further refine the "co-curriculum". Experiment results and analysis with two domains demonstrate the effectiveness of the method and the properties of data scheduled by the co-curriculum.

Keywords

Cite

@article{arxiv.1906.01130,
  title  = {Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation},
  author = {Wei Wang and Isaac Caswell and Ciprian Chelba},
  journal= {arXiv preprint arXiv:1906.01130},
  year   = {2019}
}

Comments

11 pages

R2 v1 2026-06-23T09:40:09.729Z