Download PDFOpen PDF in browserCurrent version

Directed Graph Networks for Logical Entailment

EasyChair Preprint no. 2185, version 1

Versions: 1234history
9 pagesDate: December 17, 2019


We introduce a neural model for approximating propositional entailment, a benchmark task for logical reasoning, based upon learned graph convolutions on directed graphs. The model dispenses with some of the inflexible inductive biases applied in previous work on this domain, while still producing competitive results on the dataset. In particular, model performance on larger problems surpasses all previous work.

Keyphrases: automated reasoning, directed acyclic graph, Graph Neural Network, Logical Entailment

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Michael Rawson and Giles Reger},
  title = {Directed Graph Networks for Logical Entailment},
  howpublished = {EasyChair Preprint no. 2185},

  year = {EasyChair, 2019}}
Download PDFOpen PDF in browserCurrent version