Unsupervised Learning of Semantic Relation Composition

Eduardo Blanco and Dan Moldovan
The University of Texas at Dallas


Abstract

This paper presents an unsupervised method for deriving inference axioms by composing semantic relations. The method is independent of any particular set of relation inventory. It relies on describing semantic relations using primitives and manipulating these primitives according with an algebra. The method was tested using a set of eight semantic relations yielding 78 inference axioms which were evaluated over PropBank.




Full paper: http://www.aclweb.org/anthology/P/P11/P11-1146.pdf