Findings of the Covid-19 MLIA Machine Translation Task
This work addresses the need for improved machine translation of Covid-19-related texts, but it is incremental as it reports on a community effort without introducing new methods.
The paper presents results from a community machine translation task focused on Covid-19, where nine teams competed across seven language pairs in two scenarios (with and without external data), finding that multilingual models and transfer learning performed best, with data cleaning being crucial.
This work presents the results of the machine translation (MT) task from the Covid-19 MLIA @ Eval initiative, a community effort to improve the generation of MT systems focused on the current Covid-19 crisis. Nine teams took part in this event, which was divided in two rounds and involved seven different language pairs. Two different scenarios were considered: one in which only the provided data was allowed, and a second one in which the use of external resources was allowed. Overall, best approaches were based on multilingual models and transfer learning, with an emphasis on the importance of applying a cleaning process to the training data.