The UKP Lab at Darmstadt University would like to announce its second
release:
DKPro for User-Generated Discourse 1.0 (DKPro-UGD).
User-generated discourse from Web 2.0 poses particular challenges to
natural language processing (NLP) due to its noise and error
proneness. A data cleansing step preceding the analysis steps in an
NLP pipeline can reduce the problems. DKPro for User-Generated
Discourse (DKPro-UGD) provides components for data-cleansing as well
as dictionaries for artifacts commonly found on user-generated
discourse on the web, such as emoticons, swearwords and shorthand.
DKPro-UGD is part of the comprehensive Darmstadt Knowledge Processing
Software Repository project (DKPro). DKPro leverages the flexibility
of the UIMA framework to facilitate the development and integration of
new NLP algorithms and easy configuration of NLP experiments.
The DKPro-UGD includes updated versions of some of the components that
were shipped with DKPro-Core 1.0. Most notable a new and more robust
TreeTagger wrapper component is included.
The release is freely available for research purposes and can be
obtained from the DKPro website at
http://www.ukp.tu-darmstadt.de/software/dkpro/
If you have questions or comments, please write to [email protected]
.
Best regards,
Richard Eckart de Castilho
--
-------------------------------------------------------------------
Richard Eckart de Castilho
Software Engineer
Ubiquitous Knowledge Processing Lab
FB 20 Computer Science Department
Technische Universität Darmstadt
Hochschulstr. 10, D-64289 Darmstadt, Germany
phone +49 (6151) 16 - 6218, fax -5455, room S2/02/E225
[email protected]
www.ukp.tu-darmstadt.de
-------------------------------------------------------------------
