Spectral Learning of Latent-Variable PCFGs

Shay B. Cohen; Karl Stratos; Michael Collins; Dean P. Foster; Lyle Ungar

Spectral Learning of Latent-Variable PCFGs

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English
Title of host publication	Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Place of Publication	Jeju Island, Korea
Publisher	Association for Computational Linguistics
Pages	223-231
Number of pages	9
Publication status	Published - 1 Jul 2012

Access to Document

cohen_acl2012Final published version, 209 KB

http://www.aclweb.org/anthology/P12-1024

Cite this

@inproceedings{de739aca17c94fa9985a909deb410447,

title = "Spectral Learning of Latent-Variable PCFGs",

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.",

author = "Cohen, {Shay B.} and Karl Stratos and Michael Collins and Foster, {Dean P.} and Lyle Ungar",

year = "2012",

month = jul,

day = "1",

language = "English",

pages = "223--231",

booktitle = "Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",

publisher = "Association for Computational Linguistics",

}

Spectral Learning of Latent-Variable PCFGs. / Cohen, Shay B.; Stratos, Karl; Collins, Michael et al.

Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Jeju Island, Korea : Association for Computational Linguistics, 2012. p. 223-231.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Spectral Learning of Latent-Variable PCFGs

AU - Cohen, Shay B.

AU - Stratos, Karl

AU - Collins, Michael

AU - Foster, Dean P.

AU - Ungar, Lyle

PY - 2012/7/1

Y1 - 2012/7/1

N2 - 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.

AB - 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.

M3 - Conference contribution

SP - 223

EP - 231

BT - Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

PB - Association for Computational Linguistics

CY - Jeju Island, Korea

ER -

Spectral Learning of Latent-Variable PCFGs

Abstract

Access to Document

Fingerprint

Cite this