IndexBrowse   BibliographiesMy selection
 Search: in   (word length ≥ 3)
Reference no #1120   Download bibtex file Type :   Html | Bib | Both
    Created: 2007-12-12 11:31:21
1120 Add to my selection
      AUTHOR = {Prescher, Detlef},
      TITLE = {Inside-Outside Estimation Meets Dynamic EM - GOLD},
      YEAR = {2001},
      NUMBER = {RR-01-02},
      ADDRESS = {Saarbrücken},
      TYPE = {Research Report},
      URL = {},
      ABSTRACT = {It is an interesting fact that most of the stochastic models used by linguists can be interpreted as probabilistic context-free grammars. 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 a 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 as yet imperfect line of argumentation can be transformed into a coherent proof.},
      ANNOTE = {COLIURL : Prescher:2001:IOEa.pdf}
Last modified: Thu October 16 2014 19:11:34         BibAdmin