Hi! I'm a new employee of the Internet Archive, formerly a search
engine guy, mostly working on search for the Wayback Machine. In my
spare time I've been working on a visualization of dates and entities
in scanned book contents. There's a blog post about it here:
And the demo itself is here:
I'm going to be attending the Philly conference, and I'm looking
forward to hearing from folks about other discovery tools driven
by content or algorithmic metadata.