Sarkozy, Gabor N
Selkow, Stanley M.
Our MQP aimed to introduce finite state machine based techniques for natural language processing into Hunspell, the world's premiere Open Source spell checker used in several prominent projects such as Firefox and Open Office. We created compact machine-readable finite state transducer representations of 26 of the most commonly used languages on Wikipedia. We then created an automata based spell checker. In addition, we implemented an transducer based stemmer, which will be used in the future of transducer based morphological analysis.
Worcester Polytechnic Institute
Major Qualifying Project
All authors have granted to WPI a nonexclusive royalty-free license to distribute copies of the work, subject to other agreements. Copyright is held by the author or authors, with all rights reserved, unless otherwise noted.