I have to model an AI that should be able to understand clues and find the answer from a specified word database. I came across several papers that solves the problem with training neural networks or processing the clues with training several machine learning architectures on clues that exist on several databases. However, they all seem overkill for the course currently I'm taking.

So, what would be the most simple approach to solve that problem?

  • $\begingroup$ Welcome to AI! I might suggest links to the overkill papers to provide some more specific context. This is a fairly complex problem. $\endgroup$ – DukeZhou Oct 4 '17 at 16:40
  • $\begingroup$ @DukeZhou Sure that would be awesome $\endgroup$ – Mehmet Oct 4 '17 at 17:14

Artificial neural network to solve Crossword puzzles, this model might help you to get a start on evolving your own.


A brute force of word combinations would solve the matrix, but might not get the context right and might be the simplest model if you are not in for a 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.