Identification of Entailment and Contradiction Relations between Natural Language Sentences: A Neurosymbolic Approach

TL;DR

This paper presents a neurosymbolic pipeline for natural language inference that translates text into logical form and uses automated reasoning, providing an explainable alternative to deep learning methods.

Contribution

It introduces a novel pipeline combining AMR parsing, logical translation, and SAT solving for explainable NLI, with relaxation techniques for handling linguistic variability.

Findings

Performs well on four RTE datasets

Offers explainability compared to deep learning approaches

Uses relaxation methods to improve inference accuracy

Abstract

Natural language inference (NLI), also known as Recognizing Textual Entailment (RTE), is an important aspect of natural language understanding. Most research now uses machine learning and deep learning to perform this task on specific datasets, meaning their solution is not explainable nor explicit. To address the need for an explainable approach to RTE, we propose a novel pipeline that is based on translating text into an Abstract Meaning Representation (AMR) graph. For this we use a pre-trained AMR parser. We then translate the AMR graph into propositional logic and use a SAT solver for automated reasoning. In text, often commonsense suggests that an entailment (or contradiction) relationship holds between a premise and a claim, but because different wordings are used, this is not identified from their logical representations. To address this, we introduce relaxation methods to allow replacement or forgetting of some propositions. Our experimental results show this pipeline performs well on four RTE datasets.