Count-based state merging for probabilistic regular tree grammars

Toni Dietze, Mark Jan Nederhof

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Downloads (Pure)

Abstract

We present an approach to obtain language models from a tree corpus using probabilistic
regular tree grammars (prtg). Starting with a prtg only generating trees from the corpus, the prtg is generalized step by step by merging nonterminals. We focus on bottom-up deterministic prtg to simplify the calculations.
Original languageEnglish
Title of host publicationProceedings of the 12th International Conference on Finite State Methods and Natural Language Processing
Place of PublicationDuesseldorf, Germany
PublisherAssociation for Computational Linguistics
Number of pages7
Publication statusPublished - 22 Jun 2015
EventThe 12th International Conference on Finite-State Methods and Natural Language Processing - “Haus der Universität” Düsseldorf, Düsseldorf, Germany
Duration: 22 Jun 201524 Jun 2015
http://fsmnlp2015.phil.hhu.de/

Conference

ConferenceThe 12th International Conference on Finite-State Methods and Natural Language Processing
Country/TerritoryGermany
CityDüsseldorf
Period22/06/1524/06/15
Internet address

Fingerprint

Dive into the research topics of 'Count-based state merging for probabilistic regular tree grammars'. Together they form a unique fingerprint.

Cite this