跨域推理的神经符号对比学习
Neuro-Symbolic Contrastive Learning for Cross-domain Inference
AI总结：
针对预训练语言模型在自然语言推理中过度依赖浅层启发式、归纳逻辑编程受限于离散输入的问题，提出神经符号对比学习方法，通过可微分优化提升逻辑准确性，显著增强模型跨域推理的泛化与推理能力。
摘要：
预训练语言模型（PLMs）在自然语言推理（NLI）任务中取得了显著进展，但它们对文本扰动的敏感性以及对大型数据集的依赖表明其过度依赖浅层启发式。相比之下，归纳逻辑编程（ILP）擅长在多样、稀疏且有限的数据集中推断逻辑关系，但其离散性要求输入需精确指定，限制了应用。本文提出两种方法的桥梁：神经符号对比学习。这允许平滑且可微分的优化，在逻辑函数的离散、噪声且稀疏的拓扑空间中提升逻辑准确性。我们表明，通过将数据表示为逻辑程序和逻辑规则集，抽象逻辑关系可有效嵌入神经符号范式；嵌入空间能捕捉具有相似语义逻辑关系的高度多样文本信息，还能区分具有不同逻辑关系的相似文本关系。实验结果表明，该方法在泛化性和推理能力方面显著提升了模型的推理性能。
英文摘要：
Pre-trained language models (PLMs) have made significant advances in natural language inference (NLI) tasks, however their sensitivity to textual perturbations and dependence on large datasets indicate an over-reliance on shallow heuristics. In contrast, inductive logic programming (ILP) excels at inferring logical relationships across diverse, sparse and limited datasets, but its discrete nature requires the inputs to be precisely specified, which limits their application. This paper proposes a bridge between the two approaches: neuro-symbolic contrastive learning. This allows for smooth and differentiable optimisation that improves logical accuracy across an otherwise discrete, noisy, and sparse topological space of logical functions. We show that abstract logical relationships can be effectively embedded within a neuro-symbolic paradigm, by representing data as logic programs and sets of logic rules. The embedding space captures highly varied textual information with similar semantic logical relations, but can also separate similar textual relations that have dissimilar logical relations. Experimental results demonstrate that our approach significantly improves the inference capabilities of the models in terms of generalisation and reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
