Check out the text classification software in the Mahout package.
----- Original Message ----- | From: "Jörn Kottmann" <[email protected]> | To: [email protected] | Sent: Tuesday, October 2, 2012 12:56:40 AM | Subject: Re: Bigram Likelihood | | Hello, | | the ngram package can be used to compute | the bigram counts, but there is no language model | support. | | Jörn | | On 10/02/2012 02:41 AM, Adam Goodkind wrote: | > Hi, | > | > I would like to write a program that tests the likelihood of a | > given | > program, against a "generic" language model. I realize that | > "generic" is a | > dangerous term: We'll be using data from American college students, | > if that | > helps to better define the sort of model we'd like to test against. | > Does | > OpenNLP offer anything like this? | > | > Thanks, | > Adam | > | |
