Modeling question asking using neural program generation
By ZiYun Wang, Brenden M. Lake. 2019
10 citations recorded by the source corpus.
People ask questions that are far richer, more informative, and more creative than current AI systems. We propose a neural program generation 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 ask optimal questions in synthetic settings, and 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 data.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing
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
- Mohit Bansal
- Douwe Kiela
- Luke S. Zettlemoyer
- Percy Liang
- Kyunghyun Cho
- Jacob Andreas
- Christopher D. Manning
- Wen-tau Yih
In Computer Vision and Pattern Recognition
- Mohit Bansal
- Luc Van Gool
- Trevor Darrell
- Douwe Kiela
- Dacheng Tao
- Alan L. Yuille
- Xiaogang Wang
- Andrew Zisserman
In Natural Language Processing
- Douwe Kiela
- Jacob Andreas
- Brenden M. Lake
- Mohit Bansal
- Marco Baroni
- Kyunghyun Cho
- Christopher D. Manning
- Yonatan Belinkov
Citations in the corpus
- Unsupervised Question Decomposition for Question Answering (2020, background): “Weakly supervised question generation often uses reinforcement learning (Nogueira & Cho, 2017; Wang & Lake, 2019; Strub et al., 2017; Das et al., 2017; Liang et al., 2018), where an unsupervised initialization can greatly mitigate the issues of exploring from scratch (Jaderberg et al., 2017).”
- A Benchmark for Systematic Generalization in Grounded Language Understanding (2020, methodology): “The network perceives the initial world state through a convolutional network H s = f s ( X s ) (Figure 3), using three kernel sizes (Wang & Lake, 2019).”
- Word meaning in minds and machines (2020, methodology): “than relying exclusively on neural mappings (Johnson, Hariharan, van Der Maaten, Hoffman, et al., 2017; Mao et al., 2019; Wang & Lake, 2021).”