2 Matching Annotations
  1. May 2022
    1. The source sequence will be pass to the TransformerEncoder, which will produce a new representation of it. This new representation will then be passed to the TransformerDecoder, together with the target sequence so far (target words 0 to N). The TransformerDecoder will then seek to predict the next words in the target sequence (N+1 and beyond).
  2. Feb 2016
    1. Hi! I'm interested in translate the handbook into spanish, but I have a couple of questions: 1) Is someone already doing this? and 2) is there any methodology or guidelines of the flow of information among translators?