BISTAG

Code-switching is normal in the Philippines — people mix Bisaya and Tagalog mid-sentence without thinking about it. But most NLP tools don't know what to do with that. BISTAG tackles that directly: it performs morphological decomposition and code-switching detection on mixed Bisaya-Tagalog text using an NFA-based approach. The system handles tokenization, lemmatization, POS tagging, and morphological parsing — covering affixes, reduplication, and other patterns specific to Philippine languages. It's a chrome extension too, so it's usable outside of a notebook.