论文标题
粉色：预处理的推论，最少的监督
PInKS: Preconditioned Commonsense Inference with Minimal Supervision
论文作者
论文摘要
诸如“玻璃可以用于饮用水”之类的先决条件的推理仍然是语言模型的开放问题。主要的挑战在于，前提数据的稀缺性以及模型对这种推理的缺乏支持。我们提出了粉红色的，预处理性的推论，并通过弱监督进行了改进的模型，用于通过最低限度的监督进行推理。我们从经验和理论上表明，粉红色改善了以常识性知识的前提为基准的基准（高达40％的宏观F1分数）。我们通过Pac-Bayesian信息分析，精确度量和消融研究进一步研究粉红色。
Reasoning with preconditions such as "glass can be used for drinking water unless the glass is shattered" remains an open problem for language models. The main challenge lies in the scarcity of preconditions data and the model's lack of support for such reasoning. We present PInKS, Preconditioned Commonsense Inference with WeaK Supervision, an improved model for reasoning with preconditions through minimum supervision. We show, both empirically and theoretically, that PInKS improves the results on benchmarks focused on reasoning with the preconditions of commonsense knowledge (up to 40% Macro-F1 scores). We further investigate PInKS through PAC-Bayesian informativeness analysis, precision measures, and ablation study.
