Work

Spectral Learning of Latent-Variable PCFGs

Year: 2012

Type: article

Abstract: We introduce a spectral learning algorithm for latent-variable PCFGs (Petrov et al., 2006). Under a separability (singular value) condition, we prove that the method provides consistent parameter estimates. 1

Authors: Shay B. Cohen, Karl Stratos, Michael Collins, Dean P. Foster, Lyle Ungar

Institutions: Columbia University, University of Pennsylvania

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2107484269

FWCI: 3.81

Cites: 23

Cited by: 21

Related to: 10