Skip to content
ml-recall

#1d-convolution

1 question from NLP Tasks

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

mediumAI-checkedNLP Tasks

A textCNN classifier runs 1-D convolutions over the word embeddings of a sentence: 100 filters of width 3, 100 of width 4 and 100 of width 5. Each filter's output sequence is reduced by max-over-time pooling, and the results are concatenated. How long is the resulting feature vector for a 20-word sentence?

a whole number