Optimizing Spectral Learning for Parsing

Shashi Narayan, Shay Cohen

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

Abstract

We describe a search algorithm for optimizing the number of latent states when estimating latent-variable PCFGs with spectral methods. Our results show that contrary to the common belief that the number of latent states for each nonterminal in an L-PCFG can be decided in isolation with spectral methods, parsing results significantly improve if the number of latent states for each nonterminal is globally optimized, while taking into account interactions between the different nonterminals. In addition, we contribute an empirical analysis of spectral algorithms on eight morphologically rich languages: Basque, French, German, Hebrew, Hungarian, Korean, Polish and Swedish. Our results show that our estimation consistently performs better or close to coarse-to-fine expectation-maximization techniques for these languages.
Original languageEnglish
Title of host publicationProceedings of the 54th Annual Meeting of the Association for Computational Linguistics
PublisherAssociation for Computational Linguistics
Pages1546-1556
Number of pages11
ISBN (Print)978-1-945626-01-2
DOIs
Publication statusPublished - 12 Aug 2016
Event54th Annual Meeting of the Association for Computational Linguistics - Berlin, Germany
Duration: 7 Aug 201612 Aug 2016
https://mirror.aclweb.org/acl2016/

Conference

Conference54th Annual Meeting of the Association for Computational Linguistics
Abbreviated titleACL 2016
Country/TerritoryGermany
CityBerlin
Period7/08/1612/08/16
Internet address

Cite this