Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference

TL;DR

This paper presents a neuro-symbolic natural logic framework that uses reinforcement learning and introspective revision to improve natural language inference, emphasizing interpretability, systematic generalization, and leveraging external knowledge.

Contribution

It introduces a novel neuro-symbolic approach with introspective revision and local relation models, enhancing interpretability and inference capabilities in natural language reasoning.

Findings

Outperforms previous models on existing datasets in monotonicity inference.

Demonstrates improved systematic generalization and interpretability.

Effectively leverages external knowledge to reduce spurious reasoning.

Abstract

We introduce a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision. The model samples and rewards specific reasoning paths through policy gradient, in which the introspective revision algorithm modifies intermediate symbolic reasoning steps to discover reward-earning operations as well as leverages external knowledge to alleviate spurious reasoning and training inefficiency. The framework is supported by properly designed local relation models to avoid input entangling, which helps ensure the interpretability of the proof paths. The proposed model has built-in interpretability and shows superior capability in monotonicity inference, systematic generalization, and interpretability, compared to previous models on the existing datasets.