Calling All Computer Programmers

[spiritvoyager]

I stumbled onto this webpage searching for apparently deleted articles using the names of individuals involved.  Is this some kind of Internet censorship tool??

http://www.icsi.berkeley.edu/~dgillick/names/y2_names

[Sily]

woooo.. a mystery!

Here's what he says here about where he got the names from:

Problem
In Question Answering you get a query, often with a named entity, and some documents, and you want to find relevant sentences. So it’s important to be able to match alternate versions of a name like “Muammar Gaddafi” ("Moammar El Kadhafi", "Mu'ammar al-Qadhdhafi", "Mulazim Awwal Mu'ammar Muhammad Abu Minyar al-Qadhafi", etc.).
 
Data
To study name matching, we extracted names from around 3000 documents (English newswire and blogs) and marked pairs as matched, unmatched, or ambiguous. Since there are far too many possible matches, we only considered pairs with some minimal similarity.
Name List; Labeled Data

---

He works in Artificial Intelligence I believe... here's his home page @ Berkley.