Compositional Generalization by Learning Analytical Expressions

Compositional generalization is a basic and essential intellective capability of human beings, which allows us to recombine known parts readily. However, existing neural network based models have been proven to be extremely deficient in such a capability. Inspired by work in cognition which argues compositionality can be captured by variable slots with symbolic functions, we present a refreshing view that connects a memory-augmented neural model with analytical expressions, to achieve compositional generalization. Our model consists of two cooperative neural modules, Composer and Solver, fitting well with the cognitive argument while being able to be trained in an end-to-end manner via a hierarchical reinforcement learning algorithm. Experiments on the well-known benchmark SCAN demonstrate that our model seizes a great ability of compositional generalization, solving all challenges addressed by previous works with 100% accuracies.

Authors

• Qian Liu Sea AI Lab
• Shengnan An
• Jian-Guang Lou Microsoft Research Asia
• Bei Chen
• Zeqi Lin
• Yan Gao Xiaohongshu Inc
• Bin Zhou National University of Defense Technology
• Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University
• Dongmei Zhang Peking University

Keywords

No keywords are indexed for this paper.