1 Matching Annotations
  1. May 2020
  2. mccormickml.com mccormickml.com
    BERT Word Embeddings Tutorial · Chris McCormick
    1
    1. katarzyna.rembelska 19 May 2020
      simple approach is to average the second to last hiden layer of each token producing a single 768 length vector

      Proposition how to obtain single vector for the whole sentence

      ML_CPulse embedding
    Visit annotations in context

    Tags

    Annotators

    URL

    mccormickml.com/2019/05/14/BERT-word-embeddings-tutorial/