JHU 2019 Robustness Task System Description

We describe the JHU submissions to the French–English, Japanese–English, and English–Japanese Robustness Task at WMT 2019. Our goal was to evaluate the performance of baseline systems on both the official noisy test set as well as news data, in order to ensure that performance gains in the latter did not come at the expense of general-domain performance. To this end, we built straightforward 6-layer Transformer models and experimented with a handful of variables including subword processing (FR→EN) and a handful of hyperparameters settings (JA↔EN). As expected, our systems performed reasonably.

[1]  Taku Kudo,et al.  Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates , 2018, ACL.

[2]  Taku Kudo,et al.  SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing , 2018, EMNLP.

[3]  Graham Neubig,et al.  MTNT: A Testbed for Machine Translation of Noisy Text , 2018, EMNLP.

[4]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[5]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[6]  Graham Neubig,et al.  Pointwise Prediction for Robust, Adaptable Japanese Morphological Analysis , 2011, ACL.

[7]  Matt Post,et al.  We start by defining the recurrent architecture as implemented in S OCKEYE , following , 2018 .

[8]  Kevin Duh,et al.  The JHU Machine Translation Systems for WMT 2018 , 2018, WMT.

[9]  Huda Khayrallah,et al.  Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation , 2019, NAACL.

[10]  Matt Post,et al.  A Call for Clarity in Reporting BLEU Scores , 2018, WMT.

[11]  Huda Khayrallah,et al.  Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation , 2018, NMT@ACL.

[12]  Philipp Koehn,et al.  Findings of the 2015 Workshop on Statistical Machine Translation , 2015, WMT@EMNLP.

[13]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[14]  Marcin Junczys-Dowmunt,et al.  Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corpora , 2018, WMT.