Student Work

Open Source Natural Language Processing

Pubblico

Contenuto scaricabile

open in viewer

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.

  • This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
Creator
Publisher
Identifier
  • E-project-042810-055257
Advisor
Year
  • 2010
Center
Date created
  • 2010-04-28
luogo
  • Budapest
Resource type
Major
Rights statement

Relazioni

In Collection:

Articoli

Elementi

Permanent link to this page: https://digital.wpi.edu/show/qj72p8679