This is Wencan Luo. A third-year PhD student in University of Pittsburgh.
My research interest is Natural Language Processing (NLP).

I'm interested in the idea <Natural language question answering
engine<http://wiki.dbpedia.org/gsoc2014/ideas#h359-22>>.
I know it is a difficult project since a general QA system is really hard.
However, it is a success. It will be another deep QA system like Watson and
will beat Google to some extend. I believe my NLP background, strong
programming skill and my great interest in DBpedia project can make this
project move a further step.

Luckily, QA is the final project in my NLP course (CS2731 Fall 2011) and
the QA system develop by our team (with other two students) achieved the
best performance among all the 7 teams in that class based a hybrid model
which used different models for different type of questions (why, who,
what, how, when).

I also noticed that other applicants are also interested in this project.
However, unfortunately, I missed the first Skype chat mentioned in the
mailing list. Is it possible to share the discussion results with us so
that applicants who interested in this project can also benefit from these
discussion.

One additional question for this project is that is there any training data
for this problem? (Some data including both the given query and the
corresponding answer?) If so, how big of the data size do you have?

Thanks.
Hope this inspiring project a success

-- 
Wencan Luo
CS Department- Univ. of Pittsburgh
210 S. Bouquet Street
6501 Sennott Square
Pittsburgh, PA 15260
E-mail: [email protected] or [email protected]
------------------------------------------------------------------------------
Learn Graph Databases - Download FREE O'Reilly Book
"Graph Databases" is the definitive new guide to graph databases and their
applications. Written by three acclaimed leaders in the field,
this first edition is now available. Download your free book today!
http://p.sf.net/sfu/13534_NeoTech
_______________________________________________
Dbpedia-gsoc mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc

Reply via email to