Corpus ID: 229371222

ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language

  title={ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language},
  author={Oyvind Tafjord and B. D. Mishra and P. Clark},
  • Oyvind Tafjord, B. D. Mishra, P. Clark
  • Published 2020
  • Computer Science
  • ArXiv
  • 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… CONTINUE READING


    PRover: Proof Generation for Interpretable Reasoning over Rules
    • 2
    • Highly Influential
    • PDF
    Transformers as Soft Reasoners over Language
    • 22
    • PDF
    Measuring Systematic Generalization in Neural Proof Generation with Transformers
    • 2
    • PDF
    Interpretation as Abduction
    • 832
    • PDF
    Abductive Commonsense Reasoning
    • 65
    • PDF
    Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge
    • 5
    • PDF
    e-SNLI: Natural Language Inference with Natural Language Explanations
    • 78
    • PDF
    End-to-end Differentiable Proving
    • 155
    • PDF
    Explain Yourself! Leveraging Language Models for Commonsense Reasoning
    • 86
    • PDF