2
$\begingroup$

I have trained a word2vec model using GenSim 4.

The problem is that my corpus is quite small.

How can I test the quality of the word embeddings I have obtained?

Is there some standard measures to do that?

$\endgroup$
1
  • $\begingroup$ Theoretically, a w2v model is a NN model. I think you can evaluate it as the other machine learning models. $\endgroup$
    – heroEM
    Dec 3, 2020 at 2:49

1 Answer 1

3
$\begingroup$

One way to test your embedding is see how often your model agrees with the common consensus of how other embeddings complete word analogies. A collection of established word embedding analogies are here.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.