nyanshell / GEKIKO

An Old Chinese NLP Project

GEKIKO (擊鼓)

Scripts for Old Chinese NLP work.

USAGE

N-grams

    python3 n_gram.py <input_file_or_directory>

Linguistic rules based POS tagging

    python3 pattern_predict.py <text_file> <tagged_word_list>

Count Patterns

    python3 pattern_count.py <text_file> <tagged_word_list>

WORD TAG FORMAT

Not implemented yet.