The RWTH Aachen University Machine Translation Systems for WMT 2019

Abstract

This paper describes the neural machine translation systems developed at the RWTH Aachen University for the De→En, Zh→En and Kk→En news translation tasks of the Fourth Conference on Machine Translation (WMT19). For all tasks, the final submitted system is based on the Transformer architecture. We focus on improving data filtering and fine-tuning as well as systematically evaluating interesting approaches like unigram language model segmentation and transfer learning. For the De→En task, none of the tested methods gave a significant improvement over last years winning system and we end up with the same performance, resulting in 39.6% BLEU on newstest2019. In the Zh→En task, we show 1.3% BLEU improvement over our last year's submission, which we mostly attribute to the splitting of long sentences during translation. We further report results on the Kk→En task where we gain improvements of 11.1% BLEU over our baseline system. On the same task we present a recent transfer learning approach, which uses half of the free parameters of our submission system and performs on par with it.

Findings of the 2019 Conference on Machine Translation (WMT19)

“…RUG_ENKK_BPE (Toral et al, 2019) uses data from an additional language (Russian), given the scarcity of English-Kazakh data and synthetic data (for both source and target languages) filtered using language-independent sentence similarity. (Rosendahl et al, 2019) The systems by RWTH AACHEN are all based on Transformer architecture and aside from careful corpus filtering and fine tuning, they experiment with different types of subword units. For English-German, no gains over the last year setup are observed.…”