Computers Paraphrase English

AhaIndia submits a link to a story discussing computerized paraphrasing of English news articles. This technology, destined to eventually replace most reporters with very small shell scripts, is thankfully still in its infancy.

Comments

The Ultimate Tool For Plagiarism

[popo]

All someone has to do now is marry this technology with a term-paper database, and "Hello Original Work!"

The question will then become, how many different unique "paraphrases" can the system ultimately generate?

Re:The Ultimate Tool For Plagiarism

[SurgeonGeneral]

Yes, we've all heard the arguments against cheating.

Especially the, 'you're only cheating yourself' one.

Its irrelevant because this will not affect the way we cheat so much as the way we learn and the way we write. Think about it beyond your personal experience in high school.

1. On the micro scale, an autosummerize feature like this will allow someone to take another's essay and put their facts into their own words. But I dont see how this makes any difference to the cheater other than saving him an hour. To see this tech as a problem on this level is to ignore the future.

2. On the medium scale, it will allow someone to take multiple papers, extrapolate all the facts and their sources and then string them together again with their own interpretation. This will allow the learner to come up with a new argument and possibly a fresh insight based on the available information. In this case, it saves the learner a few hours of reading, though he has to do the same amount of thinking and logical reasoning. Is it a shame that the person doesnt have to waste time reading irrelevant information? Still, looking at it on this level is not thinking very deep.

I take history in university and the essays we have to write are done by data mining books. Lots of books. We have to read large amounts of material in as short a time as possible. We have to find out what is important and what is relevant. Am I really learning how to analyze facts? I dont think so. I am learning how to write university papers and theorize based on incomplete information. I am learning how to make a lot of wasted time look like a lot of work.

3. The macro scale. What if every book ever written was replicated in full electronically and available for parsing. What if I could extrapolate every fact from every source even remotely relevant to a topic. I'm right back to where I was before : hours and hours of reading. Yet, my argument will be more solid and my information more complete then it ever could be using the outdated method of data mining: looking in the indexes of books. In this case, what am I learning? I am learning how to think. I am learning how to spot holes, inconsistancies, fallacies, and etc. In this case the technology has eliminated cheating altogether because there is no single source to copy from. And if I want to understand how all these facts are related to each other I either have to think about it or read an other authors interpretation of it. (thus I could still cheat in the classical sense)

4. But lets look at it on one more level, the very tiniest level and the most futuristic. A well constructed paragraph or sentence cant be parsed down, and wouldnt make sense if it was. The facts contained in a paragraph only become important in relation to one another. So in the end, it could just change the way we write. Enough with this puffed up crap, enough with padding your papers - either state whats important or nothing at all. A well constructed essay in the future will be one that cant be "autosummerized" without losing all its intelligability.

Something similiar existed on the Amiga

[Serk]

Back in the late 1980's I had a word processor for my Amiga that had a function whereby it would do a global search and replace of every Xth word (User settable) with a synonym from the built in Theasarus... Very handy for those term papers I so hated in high school...

I'm assuming this (Of course I didn't RTFA) is far more advanced than what we had back then, but the idea for this has been around for quite a while at least...

Someone must research a story . . .

[kfg]

conduct interviews and generate original copy. These people are called reporters.

The people who take this copy off the wire and paraphrase it for publication in the local paper are called copy writers.

This software will reduce the number of copy writers needed, not reporters.

This is certainly an issue to the copy writers and their families, but overall it's really just a blue collar worker being replaced by a robot issue.

The idea of a 'style dial' I find a bit more disturbing.

KFG

The article, summarized by MacOS X

[sakusha]

MacOS X has a summarization feature implemented in the Services menu. I decided to summarize the CNet article just to see what I got, and because I like the idea of summarizing an article about summarizing.

In the famous sketch from the TV show "Monty Python's Flying Circus," the actor John Cleese had many ways of saying a parrot was dead, among them, "This parrot is no more," "He's expired and gone to meet his maker," and "His metabolic processes are now history."
...The program gathers text from online news services on specific subjects, learns the characteristic patterns of sentences in these groupings and then uses those patterns to create new sentences that give equivalent information in different words.
The researchers, Regina Barzilay, an assistant professor in the department of electrical engineering and computer science at the Massachusetts Institute of Technology, and Lillian Lee, an associate professor of computer science at Cornell University, said that while the program would not yield paraphrases as zany as those in the Monty Python sketch, it is fairly adept at rewording the flat cadences of news service prose.

Bring on the Machines

[DumbSwede]

I don't think many people read the article. While Michael suggest this could replace reporters, it is not about summarizing a whole article, but merely paraphrasing individual sentences and elements. This would be useful for checking for plagiarism where one author has merely line by line paraphrased another. Another useful area is in language translation, where the paraphrasing may make the translation more understandable. I don't think todays translation programs allow you to say the the same thing two or three times, but repeat it back differently (paraphrase) if not understood by your listener the first time.

Of course the time will come when machines summarize articles, and I believe I have seen where this has already been tried with mixed success. It would be kind of neat to see /. use both a summary engine and a paraphrase engine on submitted articles. Then we could have 3 article descriptions: the posters description; a machine summary of the same article; and a machine paraphrase of the original posters summary.