Faster Transformer Decoding: N-gram Masked Self-Attention
Motivated by the fact that most of the information relevant to the prediction of target tokens is drawn from the source sentence S=s_1, ..., s_S, we propose truncating the target-side window used for computing self-attention by making an N-gram assumption. Experiments on WMT EnDe and EnFr data sets show that the N-gram masked self-attention model loses very little in BLEU score for N values in the range 4, ..., 8, depending on the task.
READ FULL TEXT