Please use this identifier to cite or link to this item: doi:10.22028/D291-25211
Title: Inside-outside estimation meets dynamic EM : gold
Author(s): Prescher, Detlef
Language: English
Year of Publication: 2001
OPUS Source: Kaiserslautern ; Saarbrücken : DFKI, 2001
SWD key words: Künstliche Intelligenz
DDC notations: 004 Computer science, internet
Publikation type: Report
Abstract: It is an interesting fact that most of the stochastic models used by linguists can be interpreted as probabilistic context-free grammars (Prescher 2001). In this paper, this result will be accompanied by the formal proof that the inside-outside algorithm, the standard training method for probabilistic context-free grammars, can be regarded as dynamic-programming variant of the EM algorithm. Even if this result is considered in isolation this means that most of the probabilistic models used by linguists are trained by a version of the EM algorithm. However, this result is even more interesting when considered in a theoretical context because the well-known convergence behavior of the inside-outside algorithm has been confirmed by many experiments but it seems that it never has been formally proved. Furthermore, being a version of the EM algorithm, the inside-outside algorithm also inherits the good convergence behavior of EM. We therefore contend that the yet imperfect line of argumentation can be transformed into a coherent proof.
Link to this record: urn:nbn:de:bsz:291-scidok-50019
hdl:20.500.11880/25267
http://dx.doi.org/10.22028/D291-25211
Series name: Research report / Deutsches Forschungszentrum für Künstliche Intelligenz [ISSN 0946-008x]
Series volume: 01-02
Date of registration: 5-Dec-2012
Faculty: SE - Sonstige Einrichtungen
Department: SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
File Description SizeFormat 
RR_01_02_neu.pdf2,66 MBAdobe PDFView/Open


Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.