MediumNLPnlp-368

Learned Positional Embedding Lookup

Problem

Learned positional embeddings are just an embedding table indexed by position.

Given the table as nested rows and a position, return the row.

Hint

Index the table directly, being careful to return a copy.

case 1

in: [[[0.1,0.2],[0.3,0.4]],0]

expected: [0.1,0.2]

case 2

in: [[[1,2,3]],0]

expected: [1,2,3]

case 3

in: [[[5],[6],[7]],2]

expected: [7]

Starter codePython

def learned_positional_embedding_lookup(table, position):
    # Your code here
    pass

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