Word meanings: rather than trying to use top-down dictionary definitions to get the meanings of words, researchers in 1995 tried it the way humans do it. They downloaded 300 million words of Usenet then analyzed them just for their (lexical!) context. Then the “difference” between words could be calculated, and (at least in the picture in this book) words like puppy and dog are near each other, while america and europe are far away from those but also clustered together.
things i've been impressed by lately
Word meanings: rather than trying to use top-down dictionary definitions to get the meanings of words, researchers in 1995 tried it the way humans do it. They downloaded 300 million words of Usenet then analyzed them just for their (lexical!) context. Then the “difference” between words could be calculated, and (at least in the picture in this book) words like puppy and dog are near each other, while america and europe are far away from those but also clustered together.
-
blog moved
As described elsewhere, I've quit LiveJournal. If you're interested in my continuing posts, you should look at one of these (each contains feed…
-
dremel
They published a paper on Dremel, my favorite previously-unpublished tool from the Google toolchest. Greg Linden discusses it: "[...] it is capable…
-
treemaps
I finally wrote up my recent adventures in treemapping, complete with nifty clickable visualizations.
- Post a new comment
- 4 comments
- Post a new comment
- 4 comments