Talk:Noisy channel model
This article is rated Start-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects: | ||||||||||||||
|
Scope is all wrong
[edit]"The noisy channel model is a framework used in spell checkers, question answering, speech recognition, and machine translation."
Surely the phrase "noisy channel model" is far more broadly defined than that? The best example would probably be something like the binary erasure channel rather than a spellchecker.
In other words, the article should be rewritten from the ground up, or possibly merged into Noisy channel coding theorem.
Thoughts? 84.94.180.144 (talk) 18:58, 31 July 2013 (UTC)
I absolutely agree. The problem is that the noisy channel model wasn't even developed in the context of letters in language. It has been usurped. — Preceding unsigned comment added by 104.129.194.134 (talk) 19:09, 27 May 2015 (UTC)
Shall we add reference?
Mark D. Kernighan, Kenneth W. Church, and William A. Gale. 1990. A spelling correction program based on a noisy channel model. In Proceedings of the 13th conference on Computational linguistics - Volume 2 (COLING '90), Hans Karlgren (Ed.), Vol. 2. Association for Computational Linguistics, Stroudsburg, PA, USA, 205-210. DOI=10.3115/997939.997975 http://dx.doi.org/10.3115/997939.997975 — Preceding unsigned comment added by Av life (talk • contribs) 13:08, 16 June 2015 (UTC)