SupWSD Toolkit

SupWSD is a toolkit for supervised Word Sense Disambiguation (WSD). The source code is available on GitHub.

SupWSD Toolkitversion 1.1.0(May 2019 - Size: 195 KB) MD5

Licensed under the GNU General Public License v3.0.

SupWSD API

The SupWSD API is a binding to an HTTP RESTful service that gives you programmatic access to SupWSD, a framework for supervised Word Sense Disambiguation (WSD).

SupWSD Java API Clientversion 1.2.11(October 2020 - Size: 100 KB) MD5
SupWSD Python API Clientversion 1.2.9(October 2020)

Licensed under the Creative Commons Attribution-Non Commercial-Share Alike 3.0 License.

SupWSD Pocket

SupWSD Pocket is a light version of SupWSD which allows you to perform the disambiguation offline and get the results in JSON format.

SupWSD Pocketversion 1.0.2(April 2020 - Size: 1.37 MB) MD5

Models available for specific language.

English French German Italian Spanish

Licensed under the Creative Commons Attribution-Non Commercial-Share Alike 3.0 License.

SupWSD Extension

SupWSD Extension allows you to add word sense disambiguation (WSD) and translation functionality to your Browser.

SupWSD Chrome Extensionversion 3.0(March 2020)
SupWSD Firefox Extensionversion 3.0(Coming soon)

SupWSD Trained Models

Models available for download, based on different features and corpora. All models use OpenNLP as preprocessor. The list of models and the related statistics are available here.

English French German Italian Spanish
SOW
TOM

The related model statistics are available here.

References

SupWSD: A Flexible Toolkit for Supervised Word Sense Disambiguation

Simone Papandrea, Alessandro Raganato and Claudio Delli Bovi.

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP): System Demonstrations, Copenhagen, Denmark, 7-11 September 2017, pp 103--108.

[paper] [poster] [bib]

Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in Multiple Languages without Manual Training Data

Tommaso Pasini and Roberto Navigli.

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: Copenhagen, Denmark, September 2017, pp 78--88.

[paper] [bib]

Just "OneSeC" for Producing Multilingual Sense-Annotated Data

Bianca Scarlini, Tommaso Pasini and Roberto Navigli.

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Florence, Italy, July 2019, pp 699--709.

[paper] [bib]