PhilGoetz comments on Significance of Compression Rate Method - Less Wrong

5 Post author: Daniel_Burfoot 30 May 2010 03:50AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (60)

You are viewing a single comment's thread. Show more comments above.

Comment author: PhilGoetz 01 June 2010 04:54:44PM 2 points [-]

natural language processing, where trying to formulate problems in terms of compression isn't particularly helpful

Why do you think that? Statistical natural language processing has been very successful, both for recognition and translation of text, and for speech recognition.

Comment author: rwallace 01 June 2010 07:34:42PM 0 points [-]

Statistical natural language processing yes, but that's not the same thing as text compression (again, there is a mathematical sense in which one could consider them related in principle, but doing text compression and doing natural language processing were still separate activities last I heard).