ProofWriter：在自然语言上生成蕴涵、证明和溯因语句
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
摘要：
Transformers已经被证明可以在自然语言理论（以自然语言表达的逻辑规则）上模拟逻辑演绎，可靠地将真/假标签分配给候选含义。然而，它们产生理论含义的能力尚未得到证明，并且重建答案证明的方法也不完善。在这项工作中，我们表明，生成模型，称为ProofWriter，可以可靠地生成理论的含义和支持它们的自然语言证明。特别是，迭代一步隐含生成器会产生高度可靠的证明，并代表实际的模型决策（而不是事后合理化）。在RuleTaker数据集上，ProofWriter证明的准确性超过了之前的方法+9%的绝对值，并且在某种程度上概括了训练和域外问题中看不到的证明深度。我们还表明，生成技术可以高精度地执行一种类型的溯因推理：给定一个理论和一个不可证明的结论，确定一个缺失的事实，使结论得到证明，以及一个证明。这些结果显着提高了系统推理自然语言的神经方法的可行性。
英文摘要：
Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate implications of a theory has not yet been demonstrated, and methods for reconstructing proofs of answers are imperfect. In this work we show that a generative model, called ProofWriter, can reliably generate both implications of a theory and the natural language proof(s) that support them. In particular, iterating a 1-step implication generator results in proofs that are highly reliable, and represent actual model decisions (rather than post-hoc rationalizations). On the RuleTaker dataset, the accuracy of ProofWriter's proofs exceed previous methods by +9% absolute, and in a way that generalizes to proof depths unseen in training and on out-of-domain problems. We also show that generative techniques can perform a type of abduction with high precision: Given a theory and an unprovable conclusion, identify a missing fact that allows the conclusion to be proved, along with a proof. These results significantly improve the viability of neural methods for systematically reasoning over natural language.
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。
