Apertium

Apertium is a free and open-source rule-based machine translation platform initially developed by the Transducens research group at the Universitat d'Alacant in Spain, with the first public release in 2004. The system uses a modular architecture based on finite-state transducers for lexical processing and hidden Markov models for part-of-speech tagging. Apertium is particularly effective for closely related language pairs such as Spanish-Catalan and Norwegian-Nynorsk, where structural similarities allow for more direct translation approaches. The platform supports both translation between languages with existing language pairs and the development of new pairs through its open framework.