Talking-Heads Attention (2003.02436v1)

Abstract: We introduce "talking-heads attention" - a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked LLMing tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks.