Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations

Abstract

In this work, we propose a new method to integrate two recent lines of work: unsupervised induction of shallow semantics (e.g., semantic roles) and factorization of relations in text and knowledge bases. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and… (More)

2 Figures and Tables

Topics

  • Blog articles referencing this paper

  • Presentations referencing similar topics