I want to input some words, and out comes the next word(s). Neural nets are really hot at the moment, and I'm afraid of throwing a neural net at something, when one is not really needed. Or... maybe it is needed?

My current options are:

  • Predict next word(s) using N-grams
  • Predict next word(s) using a neural net

There are quite a number of Github repositories that does this using neural nets, and a few that does it with N-grams. Are there any clear advantages to choosing the neural net approach?


You can use anything you like. Right now neural networks are the state of the art: they produce the best predictions. But you could also use HMMs, or n-grams, or other methods; they just will be lower quality than a state-of-the-art neural network.


Your Answer

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

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