2022/01/31 by Friedland, Avital, Zeltser, Jonathan, Levy, Omer
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
paper · doi:10.48550/arxiv.2201.13072
Two languages are considered mutually intelligible if their native speakers can communicate with each other, while using their own mother tongue. How does the fact that humans perceive a language pair as mutually intelligible affect the ability to learn a translation model between them? We hypothesize that the amount of data needed to train a neural ma-chine translation model is anti-proportional to the languages' mutual intelligibility. Experiments on the Romance language group reveal that there is indeed strong correlation between the area under a model's learning curve and mutual intelligibility scores obtained by studying human speakers.