Publications

WMT 2020 · Conference on Machine Translation

YerevaNN's Systems for WMT20 Biomedical Translation Task: The Effect of Fixing Misaligned Sentence Pairs

Karen Hambardzumyan, Hovhannes Tamoyan, and Hrant Khachatrian

Abstract

This report describes YerevaNN’s neural machine translation systems and data processing pipelines developed for WMT20 biomedical translation task. We provide systems for English-Russian and English-German language pairs. For the English-Russian pair, our submissions achieve the best BLEU scores, with en→ru direction outperforming the other systems by a significant margin. We explain most of the improvements by our heavy data preprocessing pipeline which attempts to fix poorly aligned sentences in the parallel data.

Citation

@inproceedings{hambardzumyan-etal-2020-yerevanns,
  title     = {{Y}ereva{NN}{'}s Systems for {WMT}20 Biomedical Translation Task:
               The Effect of Fixing Misaligned Sentence Pairs},
  author    = {Hambardzumyan, Karen and Tamoyan, Hovhannes and Khachatrian, Hrant},
  booktitle = {Proceedings of the Fifth Conference on Machine Translation},
  month     = nov,
  year      = {2020},
  address   = {Online},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2020.wmt-1.88/},
  doi       = {10.18653/v1/2020.wmt-1.88},
  pages     = {820--825}
}