Show simple item record

dc.contributor.authorBailly, Raphaël
dc.contributor.authorCarreras Pérez, Xavier
dc.contributor.authorQuattoni, Ariadna Julieta
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics
dc.date.accessioned2013-12-20T11:42:49Z
dc.date.available2013-12-20T11:42:49Z
dc.date.created2012
dc.date.issued2012
dc.identifier.citationBailly, R.; Carreras, X.; Quattoni, A.J. Unsupervised spectral learning of finite-state transducers. A: Neural Information Processing Systems Conference. "Advances in Neural Information Processing Systems 26". Lake Tahoe, Nevada: 2012, p. 800-808.
dc.identifier.urihttp://hdl.handle.net/2117/21077
dc.description.abstractFinite-State Transducers (FST) are a standard tool for modeling paired inputoutput sequences and are used in numerous applications, ranging from computational biology to natural language processing. Recently Balle et al. presented a spectral algorithm for learning FST from samples of aligned input-output sequences. In this paper we address the more realistic, yet challenging setting where the alignments are unknown to the learning algorithm. We frame FST learning as finding a low rank Hankel matrix satisfying constraints derived from observable statistics. Under this formulation, we provide identifiability results for FST distributions. Then, following previous work on rank minimization, we propose a regularized convex relaxation of this objective which is based on minimizing a nuclear norm penalty subject to linear constraints and can be solved efficiently.
dc.format.extent9 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural
dc.subject.lcshFinite-state transducers
dc.subject.otherFinite State Transducers Spectral Learning
dc.titleUnsupervised spectral learning of finite-state transducers
dc.typeConference report
dc.subject.lemacTransductors d'estats finits
dc.contributor.groupUniversitat Politècnica de Catalunya. GPLN - Grup de Processament del Llenguatge Natural
dc.contributor.groupUniversitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://papers.nips.cc/book/advances-in-neural-information-processing-systems-26-2013
dc.rights.accessOpen Access
local.identifier.drac12943366
dc.description.versionPostprint (author’s final draft)
local.citation.authorBailly, R.; Carreras, X.; Quattoni, A.J.
local.citation.contributorNeural Information Processing Systems Conference
local.citation.pubplaceLake Tahoe, Nevada
local.citation.publicationNameAdvances in Neural Information Processing Systems 26
local.citation.startingPage800
local.citation.endingPage808


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder