RNN to Transformer NMT: PyTorch Migration with 2.8x BLEU Gain
Stuck at BLEU 18 with GRU seq2seq? Here's the PyTorch code that hit BLEU 51 after migrating to Transformer—plus the causal mask bug that wasted 3 days.
Read the full article: RNN to Transformer NMT: PyTorch Migration with 2.8x BLEU Gain
You're receiving this because you subscribed to TildAlice newsletter. | #transformer, #seq2seq, #neural-machine-translation, #pytorch, #rnn-migration
Don't miss what's next. Subscribe to TildAlice Dev Weekly:
