2
$\begingroup$

I myself am not new to NLP, but for some reason I am unable to grasp purity of BERT. I have seen a ton of blogs, github repos, but none could clarify BERT usage to me.

It would be helpful if you could provide two things :

  1. A clear implementation of BERT, preferably in ipython notebook.
  2. Some papers on BERT excluding the original paper by google.
Improve this question
$\endgroup$
1
  • 1
    $\begingroup$ googles implementation is pretty good and its also in tfhub. Best rec for paper is the one on the architecture its about (the transformer-- arxiv.org/abs/1706.03762). The novelty of BERT isnt the model but the training procedure, how it claims and verifies that a bidirectional representation solving for word recovery and next sentence provides a strong contextual embedding $\endgroup$
    – mshlis
    May 26, 2019 at 4:30

0

Reset to default

You must log in to answer this question.

Browse other questions tagged .