transfix-mt/scripts/lemmatize_glossary.py
2022-01-23 16:01:44 +01:00

20 lines
607 B
Python

import nltk
import pandas as pd
from nltk.stem import WordNetLemmatizer
nltk.download('wordnet')
wl = WordNetLemmatizer()
glossary = pd.read_csv('mt-summit-corpora/glossary.tsv', sep='\t', header=None, names=['source', 'result'])
source_lemmatized = []
for word in glossary['source']:
word = nltk.word_tokenize(word)
source_lemmatized.append(' '.join([wl.lemmatize(x) for x in word]))
glossary['source_lem'] = source_lemmatized
glossary = glossary[['source', 'source_lem', 'result']]
glossary.set_index('source_lem')
glossary.to_csv('mt-summit-corpora/glossary_lem.tsv', sep='\t', index=False)