@InProceedings{aker-petrak-sabbah:2017:RANLP,
  author    = {Aker, Ahmet  and  Petrak, Johann  and  Sabbah, Firas},
  title     = {An Extensible Multilingual Open Source Lemmatizer},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Ltd.},
  pages     = {40--45},
  abstract  = {We present GATE DictLemmatizer, a multilingual open source lemmatizer for the
	GATE NLP framework that currently supports English, German, Italian, French,
	Dutch, and Spanish, and is easily extensible to other languages. The software
	is freely available under the LGPL license. The lemmatization is based on the
	Helsinki Finite-State Transducer Technology (HFST) and lemma dictionaries
	automatically created from Wiktionary. We evaluate the performance of the
	lemmatizers against TreeTagger, which is only freely available for research
	purposes. Our evaluation  shows that DictLemmatizer achieves similar or even
	better results than TreeTagger for languages where there is support from HFST.
	The performance drops when there is no support from HFST and the entire
	lemmatization process is based on lemma dictionaries. However, the results are
	still satisfactory given the fact that DictLemmatizer isopen-source and can be
	easily extended to other languages. The software for extending the lemmatizer
	by creating word lists from Wiktionary dictionaries is also freely available as
	open-source software.},
  url       = {https://doi.org/10.26615/978-954-452-049-6_006}
}