I want to take large documents and generate text that resembles them. I know that Markov Chains were used to do this with Mark V Shaney. Is there a better way to do it now, or is this approach still basically the best one available?
Share
Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
I want to take large documents and generate text that resembles them. I know that Markov Chains were used to do this with Mark V Shaney. Is there a better way to do it now, or is this approach still basically the best one available?
I am not sure whether Markov Chains are the best way of generating text but that’s surely an easy way.
There is an alternative way in deep linguistic processing using semantic to grammatical generators such as the ACE Parser/Generator. Maybe you can test the generation power of deep grammar through their demo site. After you parse a sentence on the demo site, there is an option to generate similar sentences.