Sorry, this isn't rocket science at all.<p>Standard clustering algorithms (found in any off-the-shelf natural text processing library) and text summation with libots should suffice for most of the heavy lifting.<p><a href="http://tldr.it/" rel="nofollow">http://tldr.it/</a>
<a href="http://libots.sourceforge.net/" rel="nofollow">http://libots.sourceforge.net/</a><p>Further, most news articles' first paragraph is a practical (although you may have not noticed) summary.<p>Coming from NLP, unless you can influence the source and the source being Web, the story should be an 80%-20% in the <i>best</i> case -- and you'll work VERY hard to correct the remaining 20%, and you WILL remain with a percentage of content you just can't summarize properly.<p>What <i>would</i> make a difference is a real people-driven summation, not machines (see what voicebunny did for text-to-speech, for example). And yes, it would have been fun to combine the two as well.