W3C home > Mailing lists > Public > semantic-web@w3.org > October 2010

Re: Auto tagging (or keyword discovery of) papers

From: François Dongier <francois.dongier@gmail.com>
Date: Thu, 21 Oct 2010 21:38:05 +0200
Message-ID: <AANLkTi=bnaHFwSYgf0rJHCh+KUcdBaLc34YRgN=ExuSn@mail.gmail.com>
To: Eric Hoffer <erichoffer@yahoo.com>
Cc: Jie Bao <baojie@gmail.com>, Semantic Web <semantic-web@w3.org>
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

This archive was generated by hypermail 2.4.0 : Thursday, 24 March 2022 20:41:24 UTC