Sparse and Constrained Attention for Neural Machine Translation

05/21/2018
by   Chaitanya Malaviya, et al.
0

In NMT, words are sometimes dropped from the source or generated repeatedly in the translation. We explore novel strategies to address the coverage problem that change only the attention transformation. Our approach allocates fertilities to source words, used to bound the attention each word can receive. We experiment with various sparse and constrained attention transformations and propose a new one, constrained sparsemax, shown to be differentiable and sparse. Empirical evaluation is provided in three languages pairs.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset