- Keywords: Cognitive neuroscience, Human subject research, Cognitive architecture, Neural networks architecture
- TL;DR: Our understanding of humans responding to inference tasks suggests we may need to incorporate specific biases in neuro-symbolic model architectures
- Abstract: The use of neuro-symbolic methods to supplement the performance of deep learning based natural language inference models has witnessed a resurgence. In this work, we review three sets of recent results in human cognition experiments -- in natural language comprehension, in natural language inference, and in computer program comprehension - a field bearing similarities to natural language. In light of these three works, we discuss the broader role cognitive neuroscience can play in informing the design of neuro-symbolic inference model architectures for language.
- Track: Positional paper