EasyNLPnlp-361

Dot Product Attention Scores

Problem

Unscaled attention scores are the dot products of a query with each key.

Given the query vector and the list of key vectors, return the score list.

Hint

One dot product per key.

case 1

in: [[1,0],[[1,0],[0,1]]]

expected: [1,0]

case 2

in: [[1,1],[[1,1]]]

expected: [2]

case 3

in: [[0,1],[[1,0],[0,2],[1,1]]]

expected: [0,2,1]

Starter codePython

def dot_product_attention_scores(query, keys):
    # Your code here
    pass

3 test cases · run your code against them in the editor