Skip to main content
eScholarship
Open Access Publications from the University of California

Modeling Question Asking Using Neural Program Generation

Abstract

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.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View