Latent-Variable PCFGs: Background and Applications

Shay Cohen

doi:10.18653/v1/W17-3405

Latent-Variable PCFGs: Background and Applications

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

Abstract

Latent-variable probabilistic context-free grammars are latent-variable models that are based on context-free grammars. Non-terminals are associated with latent states that provide contextual information during the top-down rewriting process of the grammar. We survey a few of the techniques used to estimate such grammars and to parse text with them. We also give an overview of what the latent states represent for English Penn treebank parsing, and provide an overview of extensions and related models to these grammars.

Original language	English
Title of host publication	Proceedings of the 15th Meeting on the Mathematics of Language
Publisher	Association for Computational Linguistics (ACL)
Pages	47–58
Number of pages	12
DOIs	https://doi.org/10.18653/v1/W17-3405
Publication status	Published - 14 Jul 2017
Event	15th Meeting on the Mathematics of Language - London, United Kingdom Duration: 13 Jul 2017 → 14 Jul 2017 http://www.molweb.org/mol2017/

Conference

Conference	15th Meeting on the Mathematics of Language
Abbreviated title	MOL 2017
Country/Territory	United Kingdom
City	London
Period	13/07/17 → 14/07/17
Internet address	http://www.molweb.org/mol2017/

Access to Document

10.18653/v1/W17-3405Licence: Creative Commons: Attribution (CC-BY)

mol17lpcfgAccepted author manuscript, 253 KB

1 Finished

SUMMA - Scalable Understanding of Mulitingual Media
Renals, S., Birch-Mayne, A. & Cohen, S.
EU government bodies
1/02/16 → 31/01/19
Project: Research

Cite this

@inproceedings{bc736f8302154096a5de1a52c284a3bd,

title = "Latent-Variable PCFGs: Background and Applications",

abstract = "Latent-variable probabilistic context-free grammars are latent-variable models that are based on context-free grammars. Non-terminals are associated with latent states that provide contextual information during the top-down rewriting process of the grammar. We survey a few of the techniques used to estimate such grammars and to parse text with them. We also give an overview of what the latent states represent for English Penn treebank parsing, and provide an overview of extensions and related models to these grammars.",

author = "Shay Cohen",

year = "2017",

month = jul,

day = "14",

doi = "10.18653/v1/W17-3405",

language = "English",

pages = "47–58",

booktitle = "Proceedings of the 15th Meeting on the Mathematics of Language",

publisher = "Association for Computational Linguistics (ACL)",

note = "15th Meeting on the Mathematics of Language , MOL 2017 ; Conference date: 13-07-2017 Through 14-07-2017",

url = "http://www.molweb.org/mol2017/",

}

TY - GEN

T1 - Latent-Variable PCFGs: Background and Applications

AU - Cohen, Shay

PY - 2017/7/14

Y1 - 2017/7/14

N2 - Latent-variable probabilistic context-free grammars are latent-variable models that are based on context-free grammars. Non-terminals are associated with latent states that provide contextual information during the top-down rewriting process of the grammar. We survey a few of the techniques used to estimate such grammars and to parse text with them. We also give an overview of what the latent states represent for English Penn treebank parsing, and provide an overview of extensions and related models to these grammars.

AB - Latent-variable probabilistic context-free grammars are latent-variable models that are based on context-free grammars. Non-terminals are associated with latent states that provide contextual information during the top-down rewriting process of the grammar. We survey a few of the techniques used to estimate such grammars and to parse text with them. We also give an overview of what the latent states represent for English Penn treebank parsing, and provide an overview of extensions and related models to these grammars.

U2 - 10.18653/v1/W17-3405

DO - 10.18653/v1/W17-3405

M3 - Conference contribution

SP - 47

EP - 58

BT - Proceedings of the 15th Meeting on the Mathematics of Language

PB - Association for Computational Linguistics (ACL)

T2 - 15th Meeting on the Mathematics of Language

Y2 - 13 July 2017 through 14 July 2017

ER -

Latent-Variable PCFGs: Background and Applications

Abstract

Conference

Access to Document

Fingerprint

Projects

SUMMA - Scalable Understanding of Mulitingual Media

Cite this