spaCy/spacy/lang/tl/lemmatizer.py

19 lines
423 B
Python

# coding: utf8
from __future__ import unicode_literals
# Adding a lemmatizer lookup table
# Documentation: https://spacy.io/docs/usage/adding-languages#lemmatizer
# Entries should be added in the following format:
LOOKUP = {
"kaugnayan": "ugnay",
"sangkatauhan": "tao",
"kanayunan": "nayon",
"pandaigdigan": "daigdig",
"kasaysayan": "saysay",
"kabayanihan": "bayani",
"karuwagan": "duwag"
}