Identification of Entailment and Contradiction Relations between Natural Language Sentences: A Neurosymbolic Approach
This work addresses the need for explainable natural language inference, which is important for applications requiring transparency in AI systems, though it is incremental as it builds on existing AMR and logic-based methods.
The authors tackled the problem of natural language inference by proposing a neurosymbolic pipeline that translates text into Abstract Meaning Representation graphs and then into propositional logic for automated reasoning, achieving strong performance on four RTE datasets.
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.