ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
@article{Tafjord2020ProofWriterGI, title={ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language}, author={Oyvind Tafjord and B. D. Mishra and P. Clark}, journal={ArXiv}, year={2020}, volume={abs/2012.13048} }
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
Figures and Tables from this paper
References
SHOWING 1-10 OF 27 REFERENCES
PRover: Proof Generation for Interpretable Reasoning over Rules
- Computer Science
- EMNLP
- 2020
- 2
- Highly Influential
- PDF
Measuring Systematic Generalization in Neural Proof Generation with Transformers
- Computer Science, Mathematics
- NeurIPS
- 2020
- 2
- PDF
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
- Computer Science
- ACL
- 2019
- 22
- PDF
Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge
- Computer Science, Psychology
- NeurIPS
- 2020
- 5
- PDF
e-SNLI: Natural Language Inference with Natural Language Explanations
- Computer Science
- NeurIPS
- 2018
- 78
- PDF