- From: François Dongier <francois.dongier@gmail.com>
- Date: Thu, 21 Oct 2010 21:38:05 +0200
- To: Eric Hoffer <erichoffer@yahoo.com>
- Cc: Jie Bao <baojie@gmail.com>, Semantic Web <semantic-web@w3.org>
Received on Thursday, 21 October 2010 19:39:12 UTC
On Thu, Oct 21, 2010 at 8:17 PM, Eric Hoffer <erichoffer@yahoo.com> wrote: > If you don't mind extracting the text first, and doing them interactively, > you can always run them through Calais [1]. > > To try a one-off of concept extraction and entity recognition, drop > something into the viewer: http://viewer.opencalais.com/ > > [1] http://www.opencalais.com/ > > > If you don't want to do it interactively, you can also use the Calais API http://www.opencalais.com/calaisAPI Annie (entity-extraction module in the Gate framework) is also worth a look. http://www.aktors.org/technologies/annie/ Best, Francois > > On Thu, Oct 21, 2010 at 12:31 PM, Jie Bao <baojie@gmail.com<http://mc/compose?to=baojie@gmail.com> > > wrote: > > Hi > > I have a few hundreds papers in pdfs [I can easily extract text from > it]. I would like to run some tools to automatically discover tags or > keywords from them. Do you have any recommendation? > > Thanks in advance > > Jie > > ----- > Jie Bao > Tetherless World Constellation > Rensselaer Polytechnic Institute > baojie@cs.rpi.edu <http://mc/compose?to=baojie@cs.rpi.edu> > http://www.cs.rpi.edu/~baojie <http://www.cs.rpi.edu/%7Ebaojie> > > > >
Received on Thursday, 21 October 2010 19:39:12 UTC