Skip to content

matthewgo/FilipinoStanfordPOSTagger

Repository files navigation

Using the Stanford part-of-speech tagger, we developed a Filipino tagger model for tagging Filipino sentences. https://paclic31.national-u.edu.ph/wp-content/uploads/2017/11/PACLIC_31_paper_5.pdf

The Stanford POS Tagger can be accessed in this website: https://nlp.stanford.edu/software/tagger.shtml

The Filipino tagger model is trained using the following feature sets: left5words, distsim, prefix(6), and prefix(2,1) and using the owlqn2 optimization. For the delimiter, we use the '|' symbol.

The tagset (list of tags) used by the Filipino tagger model can be accessed here: http://goo.gl/dY0qFe

For instructions how to use the Stanford POS Tagger and the Filipino tagger model, read through the tagger's Java documentation. The tagger may also be used in other languages as seen in the Stanford POS Tagger's homepage link above.

Releases

No releases published

Packages

No packages published