Inside-Outside Estimation Meets Dynamic EM

dc.creatorPrescher, Detlef
dc.date2004-12-03
dc.date.accessioned2026-07-07T03:22:08Z
dc.date.available2026-07-07T03:22:08Z
dc.descriptionWe briefly review the inside-outside and EM algorithm for probabilistic context-free grammars. As a result, we formally prove that inside-outside estimation is a dynamic-programming variant of EM. This is interesting in its own right, but even more when considered in a theoretical context since the well-known convergence behavior of inside-outside estimation has been confirmed by many experiments but apparently has never been formally proved. However, being a version of EM, inside-outside estimation also inherits the good convergence behavior of EM. Therefore, the as yet imperfect line of argumentation can be transformed into a coherent proof.
dc.description4 pages, some typos corrected
dc.identifierhttps://arxiv.org/abs/cs/0412016
dc.identifierhttp://arxiv.org/abs/cs/0412016
dc.identifierProceedings of IWPT 2001
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32476
dc.subjectComputation and Language
dc.titleInside-Outside Estimation Meets Dynamic EM
dc.typetext

Files

Collections