The lemmatizer for Spanish

Although open source lemmatizers for Spanish are freely available, UZEI has chosen to develop its own lemmatizer to guarantee the quality and accuracy of the lemmatization result.

This brings added value to the NLP tools developed by UZEI, which are based on its own lemmatizers, euLEMA and esLEMA.

Indeed, the fact that these two lemmatizers are based on equivalent rules and methods guarantees that the quality of corpus processing is homologous in both Basque and Spanish.

The lexical database for Spanish esLEX is based, among others, on the lemmatizer esLEMA. Like the lemmatizer for Basque, it is based on a two-level morphology and finite-state automata.