Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

From the paper:

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 ...]


> Another bug: it can sometimes lapse into an infinite loop.

That might be a bug that propagated from the politicians themselves...


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.


Yep, Markov chain generators are always fun.

I remember there being Markov chain generator for Hacker News, but it was a few months (maybe years) back.



That's more interesting than great. But:

SpaceX DSCOVR Launch – The Decision to Embrace Dinkiness

is gold.


"Interesting New Startup Developed Using The Restroom" was my favorite.


"$690 for an hour minimum wage for state management in haskell" I knew I should of learned Haskell!


"Color blind accessibility on Bootstrap and JQuery to make Vim more accessible"

This made me physically cringe.


The real thing makes me physically cringe, so I would count that as a success.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: