* * * * * * * * * * * * * * * * * * * * * * * *
LINGUIST List logo Eastern Michigan University Wayne State University *
* People & Organizations * Jobs * Calls & Conferences * Publications * Language Resources * Text & Computer Tools * Teaching & Learning * Mailing Lists * Search *
* *

LINGUIST List 25.2580

Mon Jun 16 2014

Software: Computational Linguistics, Semantics: DKPro WSD 1.1.0

Editor for this issue: Andrew Lamont <alamontlinguistlist.org>

Date: 16-Jun-2014
From: Tristan Miller <millerukp.informatik.tu-darmstadt.de>
Subject: Computational Linguistics, Semantics: DKPro WSD 1.1.0
E-mail this message to a friend

We are pleased to announce the release of DKPro WSD, version 1.1.0.

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:


In addition to various bug fixes, DKPro WSD 1.1.0 has the following new features and improvements over the previous release (1.0.0):

- Evaluators now permit chaining of backoff algorithms (Issue 29)
- Added annotators that allow for disambiguating the complete text collectively (Issue 56)
- Added a weighted MFS baseline
- Sense cluster evaluator now computes McNemar's test
- Sense cluster evaluator now handles the case where there are multiple gold-standard senses, and includes undisambiguated instances in the confusion matrix
- Improved logging output

Tristan Miller, Research Scientist
Ubiquitous Knowledge Processing Lab (UKP-TUDA)
Department of Computer Science, Technische Universit├Ąt Darmstadt
Tel: +49 6151 16 6166 | Web: http://www.ukp.tu-darmstadt.de/

Linguistic Field(s): Computational Linguistics

Read more issues|LINGUIST home page|Top of issue

Page Updated: 16-Jun-2014

Supported in part by the National Science Foundation       About LINGUIST    |   Contact Us       ILIT Logo
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed on its pages, it cannot vouch for their contents.