The Remote Associates Test (Mednick and Mednick, 1971) is a test which measures creativity as a function of ability to make remote associations. Three words are usually given, like:

and the participant is asked to come up with a fourth, which would relate to all three initial words. In this case, a good answer would be CHEESE .

When the relation between the query words and the answer is linguistic in nature, the Remote Associates Test is called a compound (or structural) test (Worthen and Clark, 1971). For example, the relation between the query words and the answer above is linguistic: COTTAGE CHEESE, SWISS CHEESE and CHEESECAKE.

comRAT-C is a computational solver which uses associative convergence principles posited by the CreaCogs framework to solve the compound Remote Associates Test. comRAT-C:

  • - solves a normative dataset of such queries (Bowden and Jung-Beeman, 2003);
  • - can offer different plausible answers and
  • - correlates in performance with humans.

See comRAT-C in action below. Queries are selected in the top part of the interface. comRAT-C tries to solve the query in the bottom part. comRAT can solve queries with or without using probability based on frequency of words. Sometimes it might not have enough knowledge to answer, it might provide a different answer than the normative data, or it could provide multiple answers.

For more details, read the paper:

  • Oltețeanu, Ana-Maria and Falomir, Zoe (2015) - comRAT-C: A Computational Compound Remote Associate Test Solver based on Language Data and its Comparison to Human Performance. Pattern Recognition Letters, vol. 67, pp. 81-90, doi:10.1016/j.patrec.2015.05.015 -- url

Other references

Bowden, E.M., Jung-Beeman, M., 2003 - Normative data for 144 compound remote associate problems Behavior Research Methods, Instruments, and Computers 35, 634–639.

Mednick, S.A., Mednick, M., 1971 - Remote associates test: Examiner’s manual. Houghton Mifflin.

Worthen, B.R., Clark, P.M., 1971. Toward an improved measure of remote associational ability. Journal of Educational Measurement 8, 113–123.