[Boards: 3 / a / aco / adv / an / asp / b / bant / biz / c / can / cgl / ck / cm / co / cock / d / diy / e / fa / fap / fit / fitlit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mlpol / mo / mtv / mu / n / news / o / out / outsoc / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / spa / t / tg / toy / trash / trv / tv / u / v / vg / vint / vip / vp / vr / w / wg / wsg / wsr / x / y ] [Search | Free Show | Home]

Automatic text spinning

This is a blue board which means that it's for everybody (Safe For Work content only). If you see any adult content, please report it.

Thread replies: 9
Thread images: 1

Did anyone here have had any success with publishing automatically "spinned" news articles? I've already consulted with a lawyer on this subject and apparently even if the text was found out as plagiarism nobody really would held responsible if the text was proven to be a result of a work of an automated script, so it seems that it might be a good idea to have a 100% passive blog which would just obtain trending topics and put out its own spin on it.

Where's the catch?
>>
>>3416172
bump
>>
So I found out something even better - that automatic translations, because they're translations, count as a derivative work and therefore cannot be considered as plagiarism.

So literally translating DailyMail to Portuguese or some other popular language would be 100% legal.

Still, why isn't everyone else doing this?
>>
Because natural language processing isn't that easy
>>
>>3416332
It wouldn't really matter if the texts were shit or not, people aren't really reading stuff, they're just looking at headers, summaries and pictures.
>>
>>3416172
>nobody really would held responsible if the text was proven to be a result of a work of an automated script

Wrong.

If the entire purpose of the script is to commit plagiarism, you're entirely responsible. If you receive a DMCA notice and refuse to comply, you're also entirely responsible.

Enjoy spending your entire life complying with lawsuit threats to run a blog that nobody even reads.
>>
>>3416332
have you fucking seen the bbc page for illiterate niggers

>eem no wipe dey ass so dey get da poopoo in da water now dey sick sick

stop acting like we have standards in this jew run world
>>
>>3416339
>If the entire purpose of the script is to commit plagiarism
But its purpose would be to find interesting topics and write articles based on the ones available online.
>>
Okay, so I've written a really simple script using nodejs' natural and here's how short text looks after it's spinned:

>'Treat these imminent extreme winds as if a tornado was approaching and move immediately to the safe room in your shelter. Take action now to protect your life. You should already be taking cover.'

vs

>'Regard these inescapable outrageous breezes as though a tornado was drawing nearer and move instantly to the protected room in your safe house. Make a move now to ensure your life. You should as of now be seeking shelter.'

So it's still rather easy to see that it's just some synonyms replaced. I was thinking about having the articles stemmed first, but maybe I could also look into some commercial "spinning" solutions?
Thread posts: 9
Thread images: 1


[Boards: 3 / a / aco / adv / an / asp / b / bant / biz / c / can / cgl / ck / cm / co / cock / d / diy / e / fa / fap / fit / fitlit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mlpol / mo / mtv / mu / n / news / o / out / outsoc / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / spa / t / tg / toy / trash / trv / tv / u / v / vg / vint / vip / vp / vr / w / wg / wsg / wsr / x / y] [Search | Top | Home]

I'm aware that Imgur.com will stop allowing adult images since 15th of May. I'm taking actions to backup as much data as possible.
Read more on this topic here - https://archived.moe/talk/thread/1694/


If you need a post removed click on it's [Report] button and follow the instruction.
DMCA Content Takedown via dmca.com
All images are hosted on imgur.com.
If you like this website please support us by donating with Bitcoins at 16mKtbZiwW52BLkibtCr8jUg2KVUMTxVQ5
All trademarks and copyrights on this page are owned by their respective parties.
Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.
This is a 4chan archive - all of the content originated from that site.
This means that RandomArchive shows their content, archived.
If you need information for a Poster - contact them.