A computer vision approach through Open AI’s CLIP, a model capable of
predicting text-image pairs, is used to create an AI agent for Dixit, a game
which requires creative linking between images and text. This paper calculates
baseline accuracies for both the ability to match the correct image to a hint
and the ability to match up with human preferences. A dataset created by
previous work on Dixit is used for testing. CLIP is utilized through the
comparison of a hint to multiple images, and previous hints, achieving a final
accuracy of 0.5011
which surpasses previous results.
References
[1]
Singh, A.K., Ding, D., Saxe, A., et al. (2022). Know Your Audience: Specializing Grounded Language Models with the Game of Dixit. arXiv: 2206.08349. https://doi.org/10.48550/arXiv.2206.08349
[2]
Roubira, J.-L. and Carpuat, M. (2008) Dixit. [Board game].
[3]
Vatsakis, D., Mavromoustakos-Blom, P. and Spronck, P. (2022). An Internet-Assisted Dixit-Playing AI. Proceedings of the 17th International Conference on the Foundations of Digital Games, Athens, 5-8 September 2022, 1-7. https://doi.org/10.1145/3555858.3555863
[4]
Radford, A., Kim, J.W., Hallacy, C., et al. (2021) Learning Transferable Visual Models from Natural Language Supervision. arXiv: 2103.00020. https://doi.org/10.48550/arXiv.2103.00020
[5]
Cherti, M., Beaumont, R., Wightman, R., et al. (2022) Reproducible Scaling Laws for Contrastive Language-Image Learning. arXiv: 2212.07143. https://doi.org/10.48550/arXiv.2212.07143
[6]
Han, J. and Kamber, M. (2008). Introduction to Data Warehousing and Mining. https://hanj.cs.illinois.edu/cs412/bk3/KL-divergence.pdf
