I have a dataset of 100000 documents each labelled with a topic to it. I want to create a model such that, given a topic, the model can generate a document from it.

I came across language models GPT, GPT-2 and BERT. I learned that they can be used for generation purposes. But I did not find anywhere whether they can generate sentences given only a word.

I am inclined to use GPT for my task, but I am not sure how to proceed with it. I wanted to know whether it is possible or not? It would be helpful if anyone can help me give a start in the right direction.

  • $\begingroup$ Why rely on models like GPT and do it manually from the array? $\endgroup$ Apr 4, 2019 at 7:59
  • $\begingroup$ Because I want to leverage the linguistics knowledge of the pre-trained models and just fine tune it to my specific task. $\endgroup$ Apr 4, 2019 at 8:30


You must log in to answer this question.

Browse other questions tagged .