�ݺ�ߣ

Monotonic Multihead Attention review

?

0 likes?179 views

Monotonic Multihead Attention, Ma, Xutai, et al. "Monotonic Multihead Attention." International Conference on Learning Representations. 2020. review by June-Woo Kim

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

Monotonic Multihead Attention review

More Related Content

Editor's Notes

#5: Simultaneous Translation is very useful in many applications.
#34: Offline: Best performance with 3 layers and 2 heads (6) MMA-H, improves in 1 layer with more heads MMA-IL: similarly to offline model. Best = 6 layers and heads (24) Latency, best performance = MMA-IL, 6 layers, 16 heads (96)