Examples of the impact of noise in NMT. The NMT systems are presented in Table 2. Vanilla NMT is trained on clean parallel data, whereas “our work” refers to the configuration #1+#2 presented in Section 5.4 trained on synthetic parallel data of UGT.
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.