1. Original Entry + Comments2. Write a Comment3. Preview Comment
New comments for this entry are disabled.

November 18, 2011  |  And now, some other text generators  |  6813 hit(s)

A little while back, I played around with various ways to create placeholder text. Those were specifically for generating nonsense text, but there are various sites/tools/utilities for generating text that have a more serious purpose. For a little Friday Fun[1], therefore, let's have a look.

Data Generator
"... a free, open source script that lets you quickly generate large volumes of custom data in a variety of formats for use in testing software, populating databases, and scoring with girls."

Ok, so that actually sounds pretty useful. (Yeah, except the girls part.) The next few are implementations of the general desire for automatic summarization.

Supposed to generate text summaries automatically from figures (e.g. in a paper). "... aggregates scattered information to improve figure comprehension. For each figure in an article, FigSum generates a structured text summary comprising one sentence from each of the four rhetorical categories – Introduction, Methods, Results and Discussion (IMRaD)."

Generating Questions Automatically from Informational Text (pdf)
"Good readers ask themselves questions during reading. The National Reading Panel reported that self-questioning was the most effective reading comprehension strategy, based on comprehension gains. So it would be useful for an intelligent tutor to automatically generate instruction for the self-questioning strategy to help students understand text. Our ultimate goal is to generate self-questioning instruction automatically from any given text, focusing on children’s text."

This one aggregates RSS feeds and republishes them as an online "newspaper":

"Paper.li is a content curation service. It enables people to publish newspapers based on topics they like and treat their readers to fresh news, daily."

Not so sure about this one, altho it is from Northwestern:

Machine-Generated Multimedia Content
"We describe an automated system, and its attendant set of techniques and tools, that is able to generate novel multimedia experiences. Using existing online sources, external textual and multimedia repositories, and user preferences, the system builds a customized audio/visual experience for the user. We discuss one application in detail: New at Seven, an automatically generated, personalized news show. Beginning with a set of user preferences, the system is able to find relevant text, process that text, and supplement it with images, video, and blogger responses. The final output of the system is an online Flash presentation that uses animated avatars with generated speech and is modeled after a traditional nightly news broadcast."

This one is a real WTF for me:

Autorewrite.com: Create Articles Automatically
"How to write an article? Our system can automatically write articles for you!

As we know articles is very important for business,especially for Internet Marketing Business.But not everybody can easily and quickly write a good article.Now with our automatic rewrite system,you can write an article with only several clicks.Those new articles are friendly to Search Engineer,Search Engineer consider it as new articles.Our article generator tools are very useful for internet marketing,bum marketing,etc.

To get new articles, you can use our Automatic Article Spinner, Synonym Tool, Keyword Tool and Smart Rewrite Tool."

And finally, the best for last. (I was kidding about all of these being for serious purposes.) You can try the following tool yourself! I myself used it to generate a paper titled "A Methodology for the Refinement of Neural Networks"[2].

SCIgen - An Automatic CS Paper Generator
"SCIgen is a program that generates random Computer Science research papers, including graphs, figures, and citations. It uses a hand-written context-free grammar to form all elements of the papers. Our aim here is to maximize amusement, rather than coherence."

The best part of SCIGen, and the stunt that really made it (in)famous, was that the students who created the tool then generated a paper that was accepted at a conference. (Not a reputable one, but still.)

[1] For some definitions of "fun."

[2] Which I see has since been, er, rejected.