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.
Abstract (translated)
自然语言推理（NLI），也称为识别文本等价性（RTE），是自然语言理解的重要方面。目前，大多数研究都使用机器学习和深度学习在特定数据集上执行此任务，这意味着他们的解决方案不可解释，也不明确。为了满足具有可解释性方法的需求，我们提出了一个新管道，该管道基于将文本转换为抽象意义表示（AMR）图。为此，我们使用了一个预训练的AMR解析器。然后将AMR图转换为命题逻辑，并使用SAT求解器进行自动推理。在文本中，通常常识表明前提与结论之间存在等价（或矛盾）关系，但因为他们使用的词汇不同，这并不能从它们的逻辑表示中识别出来。为了解决这个问题，我们引入了放松方法，允许替换或忘记某些命题。我们的实验结果表明，该管道在四个RTE数据集上的表现良好。
URL
https://arxiv.org/abs/2405.01259
