Abstract: Although most of the developing world is likely to first access the Internet through mobile phones, mobile devices are constrained by screen space, bandwidth and limited attention span. Single document summarization techniques have the potential to simplify information consumption on mobile phones by presenting only the most relevant information contained in the document. In this paper we present a language independent single-document summarization method. We map document sentences to semantic concepts in Wikipedia and select sentences for the summary based on the frequency of the mapped-to concepts. Our evaluation on English documents using the ROUGE package indicates our summarization method is competitive with the state of the art in single document summarization.
Comment. I've written a few times about document summarizing software, and how useful it will be when there is more OA literature to sic it on. But this is the first time I've seen any sign that the software could actually use OA literature to guide and improve the summaries, the way statistical machine translation software uses OA literature to guide and improve translations. Neat.
There's a nice positive feedback loop here: The more OA literature we have, the better this software will work, and the better it works, the more it supports what I call the software strategy for OA by creating new incentives to make even more work OA.
Posted by
Peter Suber at 3/10/2009 11:40:00 AM.
The open access movement:
Putting peer-reviewed scientific and scholarly literature
on the internet. Making it available free of charge and
free of most copyright and licensing restrictions.
Removing the barriers to serious research.
I recommend the OA tracking project (OATP) as the best way to stay on top of new OA developments. You can read the OATP feed on a blog-like web page or subscribe to it by RSS, email, or Twitter. You can also help build the feed by tagging new developments you encounter.
