http://mendicantbug.com/2008/04/29/late-night-spektor/ Wanderings into computational linguistics, science, social media and life... Fri, 09 Jan 2009 13:21:02 +0000 http://wordpress.org/?v=MU hourly 1 http://mendicantbug.com/2008/04/29/late-night-spektor/#comment-791 Jason Adams Fri, 02 May 2008 04:02:40 +0000 http://ealdent.wordpress.com/?p=608#comment-791 And I have no doubt that both systems (student project and Dilbertian crowdsourcing) led to far better songs than 99% of the stuff produced in any given year. And I have no doubt that both systems (student project and Dilbertian crowdsourcing) led to far better songs than 99% of the stuff produced in any given year.

]]> http://mendicantbug.com/2008/04/29/late-night-spektor/#comment-785 Chris Thu, 01 May 2008 12:25:10 +0000 http://ealdent.wordpress.com/?p=608#comment-785 Though not NLP generated, Scott Adams at his <a href="http://dilbertblog.typepad.com/the_dilbert_blog/2008/01/the-hit-song-yo.html" rel="nofollow">Dilbert Blog</a> asked his readers to create a song by each contributing one line. Then, after he posted the best version, some German band produced an MP3 of it <a href="http://www.rivodrei.de/musik/RivoDreiSheAmazedMe.mp3" rel="nofollow">here</a>. Though not NLP generated, Scott Adams at his Dilbert Blog asked his readers to create a song by each contributing one line. Then, after he posted the best version, some German band produced an MP3 of it here.

]]> http://mendicantbug.com/2008/04/29/late-night-spektor/#comment-777 Jon Elsas Tue, 29 Apr 2008 10:55:35 +0000 http://ealdent.wordpress.com/?p=608#comment-777 In my master's NLP class at UNC, one of the students' projects was doing something similar. Using a rhyming dictionary, some rough syllable analysis, vaguely thematic results from the top N pages from google and a simple HMM he created almost-sensible lyrics that rhymed and were related to a query term. I found it really entertaining and amazingly impressive for a student project. In my master’s NLP class at UNC, one of the students’ projects was doing something similar. Using a rhyming dictionary, some rough syllable analysis, vaguely thematic results from the top N pages from google and a simple HMM he created almost-sensible lyrics that rhymed and were related to a query term. I found it really entertaining and amazingly impressive for a student project.

]]>