There's certainly work in resolving and disambiguating people names in email from pre-2007.
Examples that I'm aware of include:
* Einat Minkov, Richard C. Wang, William W. Cohen, Extracting Personal Names from Emails: Applying Named Entity Recognition to Informal Text in HLT/EMNLP 2005 * Einat Minkov, William W. Cohen, Andrew Y. Ng, Contextual Search and Name Disambiguation in Email using Graphs in SIGIR 2006 (http://www.cs.cmu.edu/~einat/sigir-06.pdf) * C. P. Diehl, L. Getoor, G. Namata, "Name Reference Resolution in Organizational Email Archives," 2006 SIAM International Conference on Data Mining
I'd be interested to hear of others.
________________________________________ From: corpora-bounces at uib.no [corpora-bounces at uib.no] On Behalf Of Yorick Wilks [Yorick at dcs.shef.ac.uk] Sent: Tuesday, 2 June 2009 5:58 AM To: CORPORA List Subject: [Corpora-List] IE practice: Searching for names in emails
Does anyone recall research on the detection/annotation of proper names in emails? This has been done in Information Extraction on prose texts since the early 1990s but I see someone has patented any search for (proper) names in email text, which seems absurd in 2007. It seems to me a pubic duty to contest this kind of patenting of the obvious (and the consequent restraints on research) and Id be glad to be reminded of clear cases of pre-2007 prior art on this. Yorick Wilks]
_______________________________________________ Corpora mailing list Corpora at uib.no http://mailman.uib.no/listinfo/corpora