1
$\begingroup$

I have been going through a Ngram based Langauge Model learned using an Encoder-Decoder Model for Email smart compose.

The program output only 1 prediction for given input. I want to know how to get multiple predictions out of the same.

Here is the link to the notebook: https://nbviewer.jupyter.org/github/PrithivirajDamodaran/NLP-Experiments/blob/master/Gmail_style_smart_compose_with_char_ngram_based_language_model.ipynb

Here, for input sequence : "hi there" the predicted sequence is: ", how are you today?" But it maybe possible that I have multiple sentences starting with "hi there" in my training dataset. So how do I get all of those?

$\endgroup$

1 Answer 1

0
$\begingroup$

For your case, I feel that skip-gram model will be fit for your business problem. Where u can predict a sequence of a word rather than one word. I recommend you to train the skiagram model on your corpus.

$\endgroup$
1
  • 1
    $\begingroup$ Hey Gaurav, Thanks for the response. However,it'll be a great help if you could suggest in some way the same can be performed in the existing model $\endgroup$ Apr 10, 2020 at 9:44

Your Answer

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

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