MathOverflow is a question and answer site for professional mathematicians. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I am doing research on automatic generation of relevant mathematical exercises (similar to ones written by human) with the help of machine learning.

I have found several research papers on automatic generation of exams from a pool of exercises, but none on generating exercises with the help of machine learning.

Currently I am trying to find some relevant sources on this topic but I cannot find any.

Could anyone help me by recommending a paper on this topic?

share|cite|improve this question
There has been a lot of work on the automatic generation of text. This is the flip side of compression efficiency. However, the text generated is generally not coherent, certainly not up to the level that I would want to assign as an exercise since I would expect many of the exercises to be unsolvable. – Douglas Zare May 13 '13 at 21:16
"automatic", "relevant", "similar to ...", "mathematical" --- quite a challenging list I'd say. Maybe you could begin by creating a database of questions (taken e.g., from Polya and Szego's book)---but have you already figured out other basic issues such as: how'd you represent the input data? Maybe some work in automatic theorem proving might suggest potential automation clues.... – Suvrit May 13 '13 at 21:35

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.