While machine translation systems improved a lot over the last decade, there are still many biases and perils in their development and also in the design of automatic and manual evaluation methods. In my talk, I will focus on the following aspects: sentence-level vs. document-level, adequacy vs. fluency, source-based vs. reference-based evaluation and translationese.
*** The talk will be delivered in person (MFF UK, Malostranské nám. 25, 4th floor, room S1) and will be streamed via Zoom. For details how to join the Zoom meeting, please write to sevcikova et ufal.mff.cuni.cz ***