2
$\begingroup$

I wanted to train a chat bot for answering questions from books. I am trying to use Dynamic Memory Networks to do so.

  • How can I generate a data set like facebook did in case of babi tasks so that it can tackle a variety of questions on the data set.
$\endgroup$
2
$\begingroup$

If you are talking about "generating" in the sense of generative models , it is pretty tough. since we are still far beyond understanding the actual structure of question-answering.

And even state of the art methods for question answering are also not able to score well on datasets like babi , mostly 16 out of 20 tasks can be solved.

$\endgroup$
  • $\begingroup$ Thanks a lot for answering @thecomplexitytheorist. I wanted to create BaBI like tasks from a custom dataset - like a book. So it was not exactly like fully generating from scratch. $\endgroup$ – Shubham Bhardwaj Nov 2 '18 at 8:15
1
$\begingroup$

This repository maintained by Facebook AI Research talks about how they went about generating QA from stories.

In essence, they try to simulate how a reader reads a story. They also keep track about the knowledge the reader is assimilating when reading. Then they frame a question based on the knowledge assimilated, in order to asses if the reader can perform logical inference given what knowledge is present with him.

$\endgroup$

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.