CombiTagger is open source software intended for the development of combined taggers, independent of language and tag sets. The software, which is written in Java, was originally developed as an independent project of MA students Verena Henrich and Timo Reuter at the University of Reykjavik under the guidance of Hrafn Loftsson, during the years 2008-2009.
- Download CombiTagger from sourceforge.net. Distributed with a GPL license.
CombiTagger can be used when the outcome of two or more classifiers need to be combined, for instance by voting. CombiTagger has for instance been used to combine the outcome of a particular number (n) of taggers so that the combined tagger returns one tag for each word, for instance the tag that receives the most votes amongst the other n taggers.
- Hrafn Loftsson, Ph.D.
- Associate Professor
- Reykjavík University, School of Computer Science
- Menntavegi 1, 105 Reykjavík
- Work phone: +354-5996227
- E-mail: firstname.lastname@example.org
- Web Page: http://www.ru.is/kennarar/hrafn/
- Henrich, Verena, Timo Reuter and Hrafn Loftsson. 2009. CombiTagger: A System for Developing Combined Taggers. In Proceedings of the 22nd International FLAIRS Conference, Special Track: "Applied Natural Language Processing". Sanibel Island, Florida, USA. 2009 AAAI.
- Loftsson, Hrafn Jökull H. Yngvason, Sigrún Helgadóttir and Eiríkur Rögnvaldsson. 2010. Developing a PoS-tagged corpus using existing tools. In Proceedings of "Creation and use of basic lexical resources for less-resourced languages", workshop at the 7th International Conference on Language Resources and Evaluation, LREC 2010. Valetta, Malta.