I am supposed to build a resume parser. For the skill extraction part, currently I am matching bi-grams and uni-grams in a CV against a predefined skill set, which is not that successful. Can I train a Word2vec model so that words and phrases in a cv which could classify as skills to have similar word vectors?

Is there any method which could be more successful? Please help. Thank you in advance.

  • $\begingroup$ Did you try running word2vec already? What results did it return? $\endgroup$
    – Leevo
    Feb 25 '20 at 14:07
  • $\begingroup$ @Leevo no i did not, actually i don't know how to do it. $\endgroup$ Feb 25 '20 at 16:10
  • $\begingroup$ I suggest you to first try with word embeddings. You can do it with gensim, a Python library that allows you to train word2vec models from scratch. If it doesn't work, then you must think about something else. I can't think of a good reason why it wouldn't work. Similar skill words tend to appear in similar contexts, therefore a word2vec model should be able to learn that and represent these words close together. $\endgroup$
    – Leevo
    Feb 25 '20 at 16:53
  • $\begingroup$ @Leevo, thank you. I will try that. $\endgroup$ Feb 26 '20 at 1:29

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.