Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic
This addresses the problem of explainability in NLI for AI and NLP researchers, offering an incremental improvement by integrating fuzzy logic into existing deep learning frameworks.
The paper tackles the lack of interpretability in natural language inference (NLI) by proposing an Explainable Phrasal Reasoning (EPR) approach that uses weakly supervised logical reasoning to provide explicit explanations of phrasal relationships, and it achieves competitive performance on NLI benchmarks.
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.