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

Bhavana Dalvi Mishra
Bhavana Dalvi Mishra
Cited by: 0|Bibtex|Views5
Other Links: arxiv.org

Abstract:

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 answer...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments