Generative adversarial training for neural machine translation
Sign Up to like & getrecommendations! Published in 2018 at "Neurocomputing"
DOI: 10.1016/j.neucom.2018.09.006
Abstract: Abstract Neural machine translation (NMT) is typically optimized to generate sentences which cover n-grams with ground target as much as possible. However, it is widely acknowledged that n-gram precisions, the manually designed approximate loss function,… read more here.
Keywords: generative adversarial; csgan nmt; machine translation; model ... See more keywords