Pierre Isabelle
Sep 20, 2017 · 4 min read
  • PBMT-2: 32%
  • NMT: 53%
  • GNMT: 68%
  • While the following phenomena were completely missed by GNMT and all others systems dicussed in our paper, DEEPL managed to make a small dent into them: subject control (S2), argument switch (S7), manner-of-movement verbs (S11) and middle voice (S21).
  • Unfortunately, DEEPL turned out to be only marginally better than GNMT on idiom processing, faring worse than our PBMT-1 system, even though the latter was trained on a comparatively tiny corpus (12.1M sentence pairs).

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade