Alleviating the Inequality of Attention Heads for Neural Machine Translation

09/21/2020
by   Zewei Sun, et al.
0

Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple masking method: HeadMask, in two specific ways. Experiments show that translation improvements are achieved on multiple language pairs. Subsequent empirical analyses also support our assumption and confirm the effectiveness of the method.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset