Knowledge and Tree-Edits in Learnable Entailment Proofs
Asher Stern, Amnon Lotan, Shachar Mirkin, Eyal Shnarch, Lili Kotlerman, Jonathan Berant and Ido Dagan
In: TAC 2011, 14-15 Nov 2011, Gathersburg, MD USA.

Abstract

This paper describes B IU T EE - Bar Ilan Uni- versity Textual Entailment Engine. B IU T EE is a natural language inference system in which the hypothesis is proven by the text, based on linguistic- and world- knowledge resources, as well as syntactically motivated tree transfor- mations. The main progress in B IU T EE in the last year is a new confidence model that estimates the validity of the proof found by B IU T EE.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

[Edit]