UKB: Graph Based Word Sense Disambiguation and Similarity

UKB is a collection of programs for performing graph-based Word Sense Disambiguation and lexical similarity/relatedness using a pre-existing knowledge base.

UKB has been developed by the IXA group in the University of the Basque Country. UKB applies the so-called Personalized PageRank on a Lexical Knowledge Base (LKB) to rank the vertices of the LKB and thus perform disambiguation. The details of the method are described in [1]. It has also been applied on WSD on specific domains [2]. The algorithm can also be used to calculate lexical similarity/relatedness of words/sentences. See [3,4] for applications of UKB to similarity.

News:

02.14.2011 Version of UKB 0.1.6 is released. Click here to download UKB (unix/linux version only).
06.03.2010 Version of UKB 0.1.5r1 is released, fixing some bugs of 0.1.5. Click here to download UKB (unix/linux version only).
05.18.2010 Precompiled Personalized PageRank vectors for all WordNet lemmas (around 1.2G), useful to speed up similarity calculations. Click here to download.
05.18.2010 Version of UKB 0.1.5 is released, including scripts for similarity calculations. Click here to download UKB (unix/linux version only).
11.17.2009 Version of UKB 0.1.4 is released. Click here to download UKB (unix/linux version only).
07.13.2009 Version of UKB 0.1.3 is released. Click here to download UKB (unix/linux version only).
04.20.2009 Version of UKB 0.1.2 is released. Click here to download UKB (unix/linux version only).
03.09.2009 Version of UKB 0.1.1 is released. Click here to download UKB (unix/linux version only).
02.02.2009 Version of UKB 0.1.0 is released. Click here to download UKB (unix/linux version only).

Mailing List

Please, pose any questions/problems you may have using the following mailing list: UKB mailing list

Source code repository

to get a copy of the ukb repository run:

git clone git://ukb.git.sourceforge.net/gitroot/ukb/ukb

References

[1] Eneko Agirre and Aitor Soroa. 2009. Personalizing PageRank for Word Sense Disambiguation. Proceedings of the 12th conference of the European chapter of the Association for Computational Linguistics (EACL-2009). Athens, Greece. (PDF)

[2] Eneko Agirre, Oier Lopez de Lacalle and Aitor Soroa. 2009. Knowledge-based WSD and specific domains: performing over supervised WSD. Proceedings of IJCAI. Pasadena, USA. (PDF)

[3] Eneko Agirre, Enrique Alfonseca, Keith Hall, Jana Kravalova, Marius Pasca and Aitor Soroa. 2009. A Study on Similarity and Relatedness Using Distributional and WordNet-based Approaches. Proceedings of NAACL-HLT 09. Boulder, USA. (PDF)

[4] Eneko Agirre, Montse Cuadros, German Rigau and Aitor Soroa. 2010. Exploring Knowledge Bases for Similarity. Proceedings of LREC 2010. Valletta, Malta. (PDF)

[5] Eneko Agirre, Aitor Soroa, Mark Stevenson. 2010. Graph-based Word Sense Disambiguation of Biomedical Documents. Bioinformatics, Oxford University Press. Bioinformatics Vol. 26(22) pp: 2889-2896

Acknowledgments

This work has been partially funded by the EU Commission (project KYOTO ICT-2007-211423) and Spanish Research Department (projects KNOW TIN2006-15049-C03-01 and KNOW2 TIN2009-14715-C04-01).