LINGUIST List 24.4866|
Mon Dec 02 2013
Software: Computational Linguistics: DKPro WSD 1.0.0
Editor for this issue: Andrew Lamont
From: Tristan Miller <millerukp.informatik.tu-darmstadt.de>
Subject: Computational Linguistics: DKPro WSD 1.0.0
E-mail this message to a friend
We are pleased to announce the release of DKPro WSD, version 1.0.0.
DKPro WSD is a modular, extensible Java framework for word sense disambiguation. It provides UIMA components which encapsulate corpus readers, linguistic annotators, lexical semantic resources, disambiguation algorithms, and evaluation and reporting tools.
To obtain the software, please visit its websites on Google Code:
Following are the changes since the previous release (0.9.2).
* Support for the It Makes Sense (IMS) disambiguator. (Issue 20)
* Added a sense inventory wrapping the GermaNet Java API. (Issue 47)
* WebCAGe data set reader now works with the official release of WebCAGe. (Issue 13)
* SemCor reader now optionally writes Token, Lemma, and POS annotations. (Issue 49)
* Readers of XML-based data sets can now optionally ignore the DTD. (Issue 43)
* New wrapper module for easy disambiguation of a text string. (Issue 38)
* Senseval answer key readers now optionally normalize the sense confidence. (Issue 42)
* Cluster evaluator's output is more verbose and informative.
* Improved logging output in various modules.
* SemCor reader now sets correct annotation offsets. (Issue 52)
* Methods in si.dictionary inventories now correctly throw an exception when passed an invalid sense ID. (Issue 45)
* Restructured the package hierarchy. Users will need to update some package references (e.g., in import statements). (Issue 48)
* Upgraded to DKPro Lab 0.10.0 and TWSI 1.0.2. (Issue 33)
Tristan Miller, Research Scientist
Ubiquitous Knowledge Processing Lab (UKP-TUDA)
Department of Computer Science, Technische Universität Darmstadt
Tel: +49 6151 16 6166 | Web: http://www.ukp.tu-darmstadt.de/
Read more issues|LINGUIST home page|Top of issue
Page Updated: 02-Dec-2013
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed
on its pages, it cannot vouch for their contents.