Deep self-attention matrix model refinement

Abstract

A computing system scores importance of a number of tokens in an input token sequence to one or more prediction scores computed by a neural network model on the input token sequence. The neural network model includes multiple encoding layers. Self-attention matrices of the neural network model are received into an importance evaluator. The self-attention matrices are generated by the neural network model while computing the one or more prediction scores based on the input token sequence. Each self-attention matrix corresponds to one of the multiple encoding layers. The importance evaluator generates an importance score for one or more of the tokens in the input token sequence. Each importance score is based on a summation as a function of the self-attention matrices, the summation being computed across the tokens in the input token sequence, across the self-attention matrices, and across the multiple encoding layers in the neural network model.