Naver Labs Europe's Systems for the WMT19 Machine Translation Robustness Task
This work addresses robustness in machine translation for social media applications, but it is incremental as it builds on existing methods for a specific competition.
The paper tackled improving machine translation robustness to social media noise like informal language and spelling errors, and their ensemble models achieved first place in all language pairs according to BLEU scores in the WMT19 task.
This paper describes the systems that we submitted to the WMT19 Machine Translation robustness task. This task aims to improve MT's robustness to noise found on social media, like informal language, spelling mistakes and other orthographic variations. The organizers provide parallel data extracted from a social media website in two language pairs: French-English and Japanese-English (in both translation directions). The goal is to obtain the best scores on unseen test sets from the same source, according to automatic metrics (BLEU) and human evaluation. We proposed one single and one ensemble system for each translation direction. Our ensemble models ranked first in all language pairs, according to BLEU evaluation. We discuss the pre-processing choices that we made, and present our solutions for robustness to noise and domain adaptation.