Good examples
– cut republican billion will pay percent benefit cost
– program fund educ cut provid health help million
– economi job see need percent continu import now
– job make work compani busi right american good
– iraq war us presid support vote administr congress
These don't really look that great to me (and the 'bad examples' are worse) but I'm not an NLP expert
The stuff that you're quoting is not the stuff that the `demo.py` script generates, but "latent dirichlet allocation" (whereas this project appears to generate based on a different alternate algorithm, the sentence-based one).
The sentence-based one has a major flaw: it mostly "settles into" a given speech from its training set for a few paragraphs, then transitions to a paragraph from another speech whenever the statements become sufficiently generic.
Another bug: it can sometimes lapse into an infinite loop. Here's the tail end of one of my runs:
accordingly , the committee rose ; and the speaker pro tempore ( mrs. drake )
having assumed the chair , mr. gilchrest , acting chairman of the committee of
jurisdiction would ask the counsel to explain it ; and if it is a drafting
error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
if it is not a drafting error , then that could be corrected .
[... continues for many, many more lines before ending ...]
From a technical standpoint, the paper is somewhat lacking. It's a standard Markov-chain generator with an additional prior defined on the cohesiveness of the generated text.
I'm guessing all the press is due to it being US election season, but this is really no different from King James Programming (http://kingjamesprogramming.tumblr.com), which was entertaining, but nothing revolutionary.
Good examples – cut republican billion will pay percent benefit cost – program fund educ cut provid health help million – economi job see need percent continu import now – job make work compani busi right american good – iraq war us presid support vote administr congress
These don't really look that great to me (and the 'bad examples' are worse) but I'm not an NLP expert