Mailing-List: contact dev-help@ctakes.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@ctakes.apache.org
Received-SPF: error (athena.apache.org: local policy)
From: "Chen, Pei" <Pei.Chen@childrens.harvard.edu>
To: "dev@ctakes.apache.org" <dev@ctakes.apache.org>
Subject: RE: ClearNLP POSTagger
Thread-Topic: ClearNLP POSTagger
Thread-Index: Ac40c4Z3shxWjz1UQE6yYhmWViyLAf//+EwA//+k6AA=
Date: Mon, 8 Apr 2013 21:12:51 +0000
Message-ID: <924DE05C19409B438EB81DE683A942D9104D37FD@CHEXMBX1A.CHBOSTON.ORG>
References: <924DE05C19409B438EB81DE683A942D9104D33F7@CHEXMBX1A.CHBOSTON.ORG>
 <3563F226-D0D7-4976-9078-4684178BBD02@ukp.informatik.tu-darmstadt.de>
In-Reply-To: 
 <3563F226-D0D7-4976-9078-4684178BBD02@ukp.informatik.tu-darmstadt.de>
Accept-Language: en-US
Content-Language: en-US
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0

Hi Richard,
Yes- the ClearNLP tools (POSTagger, Dependency Parser, SRL) in cTAKES were =
retrained with additional data (MiPAQ/SHARP). =20
The Dependency Parser/SRL replaced the existing one because the old ClearPa=
rser ones were no longer supported.

The ClearPOSTagger wasn't previously available in cTAKES, but we can certai=
nly make it an optional one in case some folks may want to use it.  I'll le=
ave the default one (OpenNLP) as-is for the time being until we get some mo=
re users/tests/benchmarks/feedback...

--Pei

> -----Original Message-----
> From: Richard Eckart de Castilho [mailto:eckart@ukp.informatik.tu-
> darmstadt.de]
> Sent: Monday, April 08, 2013 1:43 PM
> To: <dev@ctakes.apache.org>
> Subject: Re: ClearNLP POSTagger
>=20
> Hi,
>=20
> did you train new models for the ClearNLP/OpenNLP tools? (Maybe I knew if
> I had followed a past discussion on models more closely.)
>=20
> Cheers,
>=20
> -- Richard
>=20
> Am 08.04.2013 um 18:15 schrieb "Chen, Pei"
> <Pei.Chen@childrens.harvard.edu>:
>=20
> > Hi,
> > While working on the Dependency Parser/SRL labeler,  we also have a
> POSTagger from ClearNLP.  It is fairly simple and I have the code ready (=
also
> trained on the same data as the dep parser- MiPaq/SHARP) to be checked-in=
.
> What does the folks think:
> > We can include both Analysis Engines in the ctakes-pos-tagger project. =
 But
> should we leave the current OpenNLP in the default pipeline or default to
> the latest?
> >
> > "The ClearNLP POS tagger shows more robust results on unknown words
> by generalizing lexical features.  You can find the reference from this p=
aper.
> > Fast and Robust Part-of-Speech Tagging Using Dynamic Model Selection,
> Jinho D. Choi, Martha Palmer, Proceedings of the 50th Annual Meeting of t=
he
> Association for Computational Linguistics (ACL'12), 363-367, Jeju, Korea,=
 2012.
> [1] It also uses AdaGrad for machine learning, which is a more advanced
> learning algorithm than maximum entropy used by OpenNLP."
> >
> > [1] http://aclweb.org/anthology-new/P/P12/P12-2071.pdf
>=20
>=20
> --
> -------------------------------------------------------------------
> Richard Eckart de Castilho
> Technical Lead
> Ubiquitous Knowledge Processing Lab (UKP-TUD)
> FB 20 Computer Science Department
> Technische Universit=E4t Darmstadt
> Hochschulstr. 10, D-64289 Darmstadt, Germany phone [+49] (0)6151 16-7477,
> fax -5455, room S2/02/B117 eckart@ukp.informatik.tu-darmstadt.de
> www.ukp.tu-darmstadt.de
> Web Research at TU Darmstadt (WeRC) www.werc.tu-darmstadt.de
> -------------------------------------------------------------------