Eingang zum Volltext in SciDok
Lizenz
Report (Bericht) zugänglich unter
Inside-outside estimation meets dynamic EM : gold
URN: urn:nbn:de:bsz:291-scidok-50019
URL: http://scidok.sulb.uni-saarland.de/volltexte/2012/5001/
Quelle:
(2001) Kaiserslautern ; Saarbrücken : DFKI, 2001
pdf-Format:
Dokument 1.pdf (2.662 KB)
SWD-Schlagwörter:
Künstliche Intelligenz
Institut:
DFKI Deutsches Forschungszentrum für Künstliche Intelligenz
DDC-Sachgruppe:
Informatik
Dokumentart:
Report (Bericht)
Schriftenreihe:
Research report / Deutsches Forschungszentrum für Künstliche Intelligenz [ISSN 0946-008x]
Bandnummer:
01-02
Sprache:
Englisch
Erstellungsjahr:
2001
Publikationsdatum:
05.12.2012
Kurzfassung auf Englisch:
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.
Lizenz:
Standard-Veröffentlichungsvertrag