A Generative-Symbolic Model for Logical Reasoning in NLU

Jidong Tian, Yitian Li, Wenqing Chen, Hao HE, Yaohui Jin

Keywords: neuro-symbolic, natural language understanding, semi-supervised learning, logical reasoning, generalization, robustness

TL;DR: A generative-symbolic model for logical reasoning in NLU

Abstract: Despite the recent success of language models (LMs) in natural language understanding (NLU), there are growing concerns about LMs' lack of logical reasoning abilities resulting in poor generalization and robustness. Faced with these concerns, neuro-symbolic integration may be a solution, which guides neural networks to understand the whole reasoning process by symbolic reasoners. In this paper, we propose a generative-symbolic model to explore how effectively this neuro-symbolic model benefits natural language understanding. The experiment on the CLUTRR dataset shows that this neural-symbolic model performs better than the corresponding neural model.

Track: Short paper