Thursday, September 27, 2007

A great application for named entity recognition

1) Locate a highly polar, drippingly opinionated piece of political bloggery.

2) Identify all person names.

3) Randomly replace them with other figures.

4) Repost the story somewhere else, and record whether anyone can detect the change.

If successful it could reduce the time required to generate political blogs by 50%, a huge gain for the economy. I just got this idea in flash while reading this. If you're interested in collaborating on this research, let me know.

2 comments:

Chris said...

Cute idea. It reminds me of a game that Language Log talked about here

Can Derrida be "even wrong"?
http://itre.cis.upenn.edu/%7Emyl/languagelog/archives/000024.html

Liberman's point is that "Derrida's admirers are generally unable to distinguish his pronouncements from their opposites at better than chance level, suggesting that the content is a sophisticated form of white noise."

PS: I found your site from your comment in Hal Daume's post on F measures.

jeanie said...

Hey, I am smruti, doing a project on named entity recognition and classification for my 6th semester project.

Based on your suggestion,you seem to be interested in this field too.

I'd love it if you could guide/help me with my project.

My email id is smruti.mja@gmail.com

Am really lookin' forward to a collaboration.