Timezone: »

Compositional Generalization via Neural-Symbolic Stack Machines
Xinyun Chen · Chen Liang · Adams Wei Yu · Dawn Song · Denny Zhou

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #794

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 four domains: the SCAN benchmark of language-driven navigation tasks, the task of few-shot learning of compositional instructions, the compositional machine translation benchmark, and context-free grammar parsing tasks.

Author Information

Xinyun Chen (UC Berkeley)
Chen Liang (Google Brain)
Adams Wei Yu (Google Brain)
Dawn Song (UC Berkeley)
Denny Zhou (Google Brain)

More from the Same Authors