I am one of the engineers who built the Google Books NGram Viewer. +Yuan K Shen and I (mostly him) also did the underlying corpus generation and analysis during his internship with Google. It was a great pleasure to work with Erez & JB on their research and now they have given an excellent (and amusing) TED talk on the work.
http://www.ted.com/talks/what_we_learned_from_5_million_books.html
(I am also happy to answer questions or otherwise discuss the data, viewer, tools and research here on Plus)
http://www.ted.com/talks/what_we_learned_from_5_million_books.html
(I am also happy to answer questions or otherwise discuss the data, viewer, tools and research here on Plus)
What we learned from 5 million books | Video on TED.com
H Vandagriff - 2011-09-25 19:29:41-0400
Brilliant presentation, awesome work. Thank you.
Riff Zifnab - 2011-09-25 21:31:22-0400
Arrrrg, that picture's not from XKCD! ):< (Stand back, I will do science to it)
Ivano Forgione - 2011-09-26 13:07:42-0400
please, add italian to the library! :) any chance?