Comments on: Mechanical Turkey http://thenoisychannel.com/2008/11/27/mechanical-turkey/ Sat, 11 Feb 2012 00:39:47 +0000 hourly 1 http://wordpress.org/?v=3.3.1 By: Daniel Tunkelang http://thenoisychannel.com/2008/11/27/mechanical-turkey/comment-page-1/#comment-1044 Daniel Tunkelang Sat, 06 Dec 2008 22:55:00 +0000 http://thenoisychannel.com/?p=866#comment-1044 Well, I'm glad that the IR community is growing more open to cost-effective evaluation strategies that don't require trained assessors. I'm hopeful that this openness will in turn lead to work on interactive IR becoming more mainstream, since--at least as I understand it--the bottleneck of such research is the cost of evaluation. Well, I’m glad that the IR community is growing more open to cost-effective evaluation strategies that don’t require trained assessors. I’m hopeful that this openness will in turn lead to work on interactive IR becoming more mainstream, since–at least as I understand it–the bottleneck of such research is the cost of evaluation.

]]> By: Brendan O'Connor http://thenoisychannel.com/2008/11/27/mechanical-turkey/comment-page-1/#comment-984 Brendan O'Connor Sat, 29 Nov 2008 01:04:15 +0000 http://thenoisychannel.com/?p=866#comment-984 hah, they cited out blog post! hah, they cited out blog post!

]]> By: Brendan O'Connor http://thenoisychannel.com/2008/11/27/mechanical-turkey/comment-page-1/#comment-983 Brendan O'Connor Sat, 29 Nov 2008 01:02:49 +0000 http://thenoisychannel.com/?p=866#comment-983 We did this at Dolores Labs earlier this year. Here's one public blog post we wrote -- http://blog.doloreslabs.com/2008/04/search-engine-relevance-an-empirical-test/ though we didn't rigorously evaluate the data in that particular study; (like we did for NLP, http://blog.doloreslabs.com/2008/09/amt-fast-cheap-good-machine-learning/ ) We did this at Dolores Labs earlier this year. Here’s one public blog post we wrote — http://blog.doloreslabs.com/2008/04/search-engine-relevance-an-empirical-test/

though we didn’t rigorously evaluate the data in that particular study; (like we did for NLP, http://blog.doloreslabs.com/2008/09/amt-fast-cheap-good-machine-learning/ )

]]>