Question Asking as Program Generation

By Anselm Rothe, Brenden M. Lake, Todd M. Gureckis. 2017

51 citations recorded by the source corpus.

A hallmark of human intelligence is the ability to ask rich, creative, and revealing questions. Here we introduce a cognitive model capable of constructing human-like questions. Our approach treats questions as formal programs that, when executed on the state of the world, output an answer. The model specifies a probability distribution over a complex, compositional space of programs, favoring concise programs that help the agent learn in the current context. We evaluate our approach by modeling the types of open-ended questions generated by humans who were attempting to learn about an ambiguous situation in a game. We find that our model predicts what questions people will ask, and can creatively produce novel questions that were not present in the training set. In addition, we compare a number of model variants, finding that both question informativeness and complexity are important for producing human-like questions.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Few-Shot Learning with Graph Neural Networks (2017, neutral): “Following several recent works that cast posterior inference using message passing with neural networks defined over graphs Scarselli et al. (2009); Duvenaud et al.”
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding (2018, background): “In particular, Andreas et al. [2016] attempted to use the latent structure in language to help question answering and reasoning, Rothe et al. [2017] studied the use of formal programs in modeling human questions, and Goldman et al. [2017] used abstract examples to build weakly-supervised semantic…”
Modeling question asking using neural program generation (2019, methodology): “In order to calculate the log-likelihood of human questions, we use translated versions of these questions that were used in previous work [16], and filtered some human questions that score poorly according to the generative model used for training the neural network (Appendix A.”
What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog. (2019, unknown): “(Rothe et al., 2017) proposed a model that generates questions in a Battleship game scenario.”
Learning by Asking Questions (2017, background): “Visual question generation (VQG) was recently proposed as an alternative to image captioning [34, 38, 42].”