What is a good (free or low-cost) program to mine text from large numbers of patents?

June 29, 2007 4:52 PM

What is a good (free or low-cost) program to mine text from large numbers of patents?

I'm looking for a text analysis tool to help me organize information from large numbers of patents into categories or clusters. There are commercial applications that do this, but they are exceedingly expensive. Ideally, I would like to be able to dump the results of my database query into the program and let it go to work to identify relationships between things that are non-intuitive and/or obscured due to huge amounts of information.

Thanks for any suggestions.

posted by underdetermined to computers & internet (1 comment total)

There's CRM114, best known for spam filtering but also usable as a general-purpose text classifier.
posted by mbrubeck at 8:40 PM on June 29, 2007