ML Anthology

Learning from Entailment: An Application to Propositional Horn Sentences

Michael Frazier, Leonard Pitt
ICML 1993 pp. 120-127
doi:10.1016/B978-1-55860-307-3.50022-8 /icml/1993/frazier1993icml-learning/

Abstract

Let ϕ be an unknown theory. Can ϕ be efficiently inferred given examples of statements that ϕ entails and statements that ϕ does not entail? It is shown that if ϕ is a propositional Horn sentence, then ϕ can be efficiently learned in this model when the entailed statements are also Horn sentences. An application of the learning algorithm to the area of approximate entailment is discussed.

ICML Semantic Scholar

Cite

Text

Frazier and Pitt. "Learning from Entailment: An Application to Propositional Horn Sentences." International Conference on Machine Learning, 1993. doi:10.1016/B978-1-55860-307-3.50022-8

Markdown

[Frazier and Pitt. "Learning from Entailment: An Application to Propositional Horn Sentences." International Conference on Machine Learning, 1993.](https://mlanthology.org/icml/1993/frazier1993icml-learning/) doi:10.1016/B978-1-55860-307-3.50022-8

BibTeX

@inproceedings{frazier1993icml-learning,
  title     = {{Learning from Entailment: An Application to Propositional Horn Sentences}},
  author    = {Frazier, Michael and Pitt, Leonard},
  booktitle = {International Conference on Machine Learning},
  year      = {1993},
  pages     = {120-127},
  doi       = {10.1016/B978-1-55860-307-3.50022-8},
  url       = {https://mlanthology.org/icml/1993/frazier1993icml-learning/}
}