Compositional Generalization via Neural-Symbolic Stack Machines

NIPS 2020(2020)

引用 74|浏览169
暂无评分
摘要
Despite achieving tremendous success, existing deep learning models have exposed limitations in compositional generalization, the capability to learn compositional rules and apply them to unseen cases in a systematic manner. To tackle this issue, we propose the Neural-Symbolic Stack Machine (NeSS). It contains a neural network to generate traces, which are then executed by a symbolic stack machine enhanced with sequence manipulation operations. NeSS combines the expressive power of neural sequence models with the recursion supported by the symbolic stack machine. Without training supervision on execution traces, NeSS achieves 100% generalization performance in three domains: the SCAN benchmark of language-driven navigation tasks, the compositional machine translation benchmark, and context-free grammar parsing tasks.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络