People ask questions that are far richer, more informative, and more creative than current AI systems. We propose a neuro-symbolic framework for modeling human question asking, which represents questions as formal programs and generates programs with an encoder-decoder based deep neural network. From extensive experiments using an information-search game, we show that our method can predict which questions humans are likely to ask in unconstrained settings. We also propose a novel grammar-based question generation framework trained with reinforcement learning, which is able to generate creative questions without supervised human data.
@article{arxiv.1907.09899,
title = {Modeling question asking using neural program generation},
author = {Ziyun Wang and Brenden M. Lake},
journal= {arXiv preprint arXiv:1907.09899},
year = {2021}
}
Comments
Please cite as: Wang, Z. and Lake, B. M. (2021). Modeling question asking using neural program generation. In Proceedings of the 43rd Annual Conference of the Cognitive Science Society