CTO Franck Burlot, in co-working with the LIUM Lab from Le Mans University, organised a research task in the context of the upcoming WMT19 Conference on Machine Translation.
Franck additionally contributed to that task by providing a dedicated system that he will be presenting on the 1st and 2nd of August in Florence.
WMT is the annual competition where major MT players, both academic and industry-side, are evaluated and compared: http://www.statmt.org/wmt19/translation-task.html
This paper describes Lingua Custodia’s submission to the WMT’19 news shared task for German-to-French on the topic of the EU elections. We report experiments on the adaptation of the terminology of a machine translation system to a specific topic, aimed at providing more accurate translations of specific entities like political parties and person names, given that the shared task provided no in-domain training parallel data dealing with the restricted topic. Our primary submission to the shared task uses backtranslation generated with a type of decoding allowing the insertion of constraints in the output in order to guarantee the correct translation of specific terms that are not necessarily observed in the data.
Read the extensive article here.