Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

TL;DR

This paper introduces an explainable neural model for natural language inference that uses weakly supervised logical reasoning with fuzzy logic to provide explicit, interpretable phrase-level explanations.

Contribution

It proposes a novel weakly supervised phrasal reasoning approach using fuzzy logic, enabling end-to-end training and interpretability in NLI models.

Findings

Model achieves interpretable phrase-level explanations.

End-to-end differentiable system trained with weak supervision.

Improves textual explanation generation quality.

Abstract

Natural language inference (NLI) aims to determine the logical relationship between two sentences, such as Entailment, Contradiction, and Neutral. In recent years, deep learning models have become a prevailing approach to NLI, but they lack interpretability and explainability. In this work, we address the explainability of NLI by weakly supervised logical reasoning, and propose an Explainable Phrasal Reasoning (EPR) approach. Our model first detects phrases as the semantic unit and aligns corresponding phrases in the two sentences. Then, the model predicts the NLI label for the aligned phrases, and induces the sentence label by fuzzy logic formulas. Our EPR is almost everywhere differentiable and thus the system can be trained end to end. In this way, we are able to provide explicit explanations of phrasal logical relationships in a weakly supervised manner. We further show that such reasoning results help textual explanation generation.