[Metadatalibrarians] Metadata Remediation Tools

[Greta de Groat]

My apologies if this shows up multiple times, i keep getting messages  
that it was rejected:

Thanks a lot, Gunther, for the list of tools from the forum last  
month. Interestingly, i can see that many of them seem primarily for  
use with MARC records.

It seems like there are a fair number of tools to create metadata  
records, validate formats and check for missingdata.  Is there anyone  
out there who is programatically supplying missing data for already  
created metadata records?  I've seen an interesting article on  
extracting names from statements of esponsibility in the Levy Sheet  
Music collection, but the article was from 2001.  Has anyone else  
worked on something similar since?  In the private sector right now  
there is a lot of work on entity extraction and semantic markup, so  
i'm wondering if any libraries are trying out these tools or building  
ones of their own.

Is anybody trying to work with genres? (or even define them?)

Did anybody attend the ACM/IEEE-CS joint conference on Digital  
Libraries in Pittsburgh last week?  There are some interesting  
sounding abstracts, but as of Friday anyway the papers weren't yet  
available.  Does anybody have any comments on any of the ideas  
circulated there?

Thanks
greta de groat
Stanford University Libraries