psi-toolkit

Project factsheet

English name:	Publicly available tools for automatic processing of Polish language
Polish name:	Narzędzia do automatycznego przetwarzania języka polskiego udostępnione publicznie
Project type:	A national Ministry of Science and Higher Education research grant (number N N516 480540)
Duration:	2011 ‒ 2013
Principal investigator:	Krzysztof Jassem
Institution:	Information Systems Laboratory, Faculty of Mathematics and Computer Science, Adam Mickiewicz University

Project description

The aim of the project is to develop a tool chain (called psi-toolkit) for automatic processing of Polish (and - to lesser extent - other languages: English, German, French, Spanish and Russian) with the focus on machine translation. The tool chain will include:

segmentation/tokenization/lemmatization,
shallow parsing,
deep parsing,
rule-based machine translation,
statistical machine translation,
automatic generation of inflected forms from lemma sequences
automatic postedition.

All the tools will be publicly available under the LGPL licence.