nlp the beginning
Dec. 16th, 2011 08:56 pm![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
vlionI've thought for years I wanted to do natural language processing/computational linguistics research.
Well, I'm making first steps. There's a book here: http://nlp.stanford.edu/IR-book/.
Then in the spring the Stanford NLP class will be broadcast: http://www.nlp-class.org
I'm going to put together a 'corpus' of texts and use it for my initial messing around.
Turns out if you go to http://www.gutenberg.org/ebooks/ and append a number to the book you can get each book. So I'll grab the first 9 as my corpus (10 is the Bible and thus many works), and also "A Declaration of the Independence of Cyberspace" .
I'll be putting them up on bitbucket shortly. /woo
Well, I'm making first steps. There's a book here: http://nlp.stanford.edu/IR-book/.
Then in the spring the Stanford NLP class will be broadcast: http://www.nlp-class.org
I'm going to put together a 'corpus' of texts and use it for my initial messing around.
Turns out if you go to http://www.gutenberg.org/ebooks/ and append a number to the book you can get each book. So I'll grab the first 9 as my corpus (10 is the Bible and thus many works), and also "A Declaration of the Independence of Cyberspace" .
I'll be putting them up on bitbucket shortly. /woo
