#39: MLDublin meets to talk about Machine Translation- 1 min
In this talk we will be reviewing several approaches which have been proposed to build machine translation (MT) systems for low resource language pairs. We will also give a summary of these methods and how they perform in specific language pairs.
How much language do Machine Translation (MT) systems learn? How much do they lose compared to Human Translation (HT)? This work presents extensive empirical evaluation on machine and human translations aiming to answer these questions. We show how MT systems indeed fail to render the lexical diversity of human generated or translated text. The inability of MT systems to generate diverse outputs and its tendency to exacerbate already frequent patterns while ignoring less frequent ones, might be the underlying cause for, among others, the currently heavily debated issues related to gender biased output. Can we indeed, aside from biased data, talk about an algorithm that exacerbates seen biases?