--- In FairfieldLife@yahoogroups.com, "Ann" <awoelflebater@...> wrote:
> Ok, that was silly. I went to your link and typed in some text. I made it > longer and played with the percentage to keep or edit. All it did was > randomly leave in or take out stuff. I don't get why you need a program to do > this. Many of us do it naturally by the way we read, which is often sloppy > or, because of pre-conceived notions about things, we fail to take in half of > what anyone is actually saying. All of us are text compactors already and I > don't think it benefits us all that much. I don't require a computer to do it > FOR me! This kind of software is designed to produce 'executive summaries', and well designed programs do not use random selection. However the sample of Robin's was huge, and the compression was to about 5% which is really far too much. Normally you get reasonable results with 25% to 50% compression. Some manual editing might be needed. The software works better if the original document has a well defined structure. 'HOW IT WORKS' 'After text is placed on the page, the web app calculates the frequency of each word in the passage. Then, a score is calculated for each sentence based on the frequency count associated with the words it contains. The most important sentence is deemed to be the sentence with the highest frequency count.' 'Obviously, human readers may disagree with this automated approach to text summarization. Automated text summarization works best on expository text such as textbooks and reference material (non-fiction). The results can be skewed when a passage has only a few sentences. Text Compactor is not recommended for use with fiction (i.e., stories about imaginary people, places, events).' As the result with that post was not particularly good, I conclude Robin and his exposition is the result of an imaginary person writing about imaginary places and events, though Ann and Curtis seem reasonably real. But of course I can't be sure. Everyone on this forum is just text on a screen to me.