Evolution of Attention [Part 2. Improved Alignment / Attention] (opens in new tab)
In Part 1, we saw how Bahdanau gave the decoder a way to look back — at every step, the alignment model scans all encoder states…
Read the original articleIn Part 1, we saw how Bahdanau gave the decoder a way to look back — at every step, the alignment model scans all encoder states…
Read the original article