Latent-Variable PCFGs: Background and Applications

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish
Title of host publicationProceedings of the 15th Meeting on the Mathematics of Language
PublisherAssociation for Computational Linguistics (ACL)
Pages47–58
Number of pages12
DOIs
Publication statusPublished - 14 Jul 2017
Event15th Meeting on the Mathematics of Language - London, United Kingdom
Duration: 13 Jul 201714 Jul 2017
http://www.molweb.org/mol2017/

Conference

Conference15th Meeting on the Mathematics of Language
Abbreviated titleMOL 2017
Country/TerritoryUnited Kingdom
CityLondon
Period13/07/1714/07/17
Internet address

Fingerprint

Dive into the research topics of 'Latent-Variable PCFGs: Background and Applications'. Together they form a unique fingerprint.

Cite this