Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete Reasoning

By Moxin Li, Fuli Feng, Hanwang Zhang, Xiangnan He, Fengbin Zhu, Tat-seng Chua. 2022

40 citations recorded by the source corpus.

Neural discrete reasoning (NDR) has shown remarkable progress in combining deep models with discrete reasoning. However, we find that existing NDR solution suffers from large performance drop on hypothetical questions, e.g. “what the annualized rate of return would be if the revenue in 2020 was doubled”. The key to hypothetical question answering (HQA) is counterfactual thinking, which is a natural ability of human reasoning but difficult for deep models. In this work, we devise a Learning to Imagine (L2I) module, which can be seamlessly incorporated into NDR models to perform the imagination of unseen counterfactual. In particular, we formulate counterfactual thinking into two steps: 1) identifying the fact to intervene, and 2) deriving the counterfactual from the fact and assumption, which are designed as neural networks. Based on TAT-QA, we construct a very challenging HQA dataset with 8,283 hypothetical questions. We apply the proposed L2I to TAGOP, the state-of-the-art solution on TAT-QA, validating the rationality and effectiveness of our approach.

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

1. Qian Liu
2. Jian-Guang Lou
3. Zeqi Lin
4. Qiang Fu
5. Xinyu Pi
6. Yan Gao
7. Morteza Ziyadi
8. Weizhu Chen

In Computer Vision and Pattern Recognition

1. Jian-Guang Lou
2. Zeqi Lin
3. Qiang Fu
4. Qian Liu
5. Yan Gao
6. Weizhu Chen
7. Jianfeng Gao
8. Samuel R. Bowman

In Natural Language Processing

1. Qian Liu
2. Yan Gao
3. Morteza Ziyadi
4. Weizhu Chen
5. Qiang Fu
6. Zeqi Lin
7. Jian-Guang Lou
8. Jianfeng Gao

Citations in the corpus

• Reasoning Like Program Executors (2022, background): “Reasoning in Giant Language Models Recent works demonstrate that with proper prompting (e.g., chain-of-thoughts prompting), giant language models (e.g., GPT-3) can perform well on reasoning tasks (Wei et al., 2022; Kojima et al., 2022; Li et al., 2022b).”