A
lemmatizer is a program that finds a word's lemma or lemmas.
The lemma is the head word of a morphological family, the root; it is the word
that we would be difined in a dictionary.
Most words in Spanish are inflected words. Given an inflected word, this program
obtains its lemma and the meaning of its inflection.
For example, given the word "perritas" the lemmatizer will determine it comes
from the lemma "perro" with the attributes femenine, plural and diminutive.
Similarly, if we enter the word "leerá",
the program will reveal it's the third person, singular, of the future indicative of
the verb "leer".
The lemmatizer can find all possible lemmas of a given word, thus, the lemmatizer
will inform us that for the word
"suma":
- It is the root of the noun "suma".
- It is the third person singular of the present indicative
of the verb "sumar".
- It is the third person singular of the imperative of the
verb "sumir".
- It is the femenine singular of the adjective "sumo".