Added words_to_lem.py script that lemmatizes entire text corpora using PSI-TOOLKIT
Feel free to use this tool if you cite: Wołk K., Marasek K., “Polish – English Speech Statistical Machine Translation Systems for the IWSLT 2013.”, Proceedings of the 10th International Workshop on Spoken Language Translation, Heidelberg, Germany, p. 113-119, 2013
For more information, see: http://arxiv.org/pdf/1509.09097
For any questions: | Krzysztof Wolk | krzysztof@wolk.pl