KUKoLex

KUKoLex is a Korean morphological analyzer and tagger made by NLP&AI LAB at Korea University. Main functions are as follows.

Requirements

Python 3

Install

From PyPi:

    pip install kukolex

From GitHub:

    pip install git+https://github.com/nlpai-lab/KU_KoLex.git

Usage

• pos_tagging(input)

It takes "sentences" as an input and gives a list of morphemes and their POS tags as an output

• morphs(input)

It takes "sentences" as an input and gives a list of morphemes.

• pos(input)

It takes "sentences" as an input and gives a list of POS tags.

• nouns(input)

It takes "sentences" as an input and gives a list of nouns.

    from KUKoLex import kukolex

    kukolex.pos_tagging('안녕하세요. 저의 이름은 홍길동입니다.')
    # [('안녕', 'NNG'), ('하', 'XSA'), ('시', 'EP'), ('어요', 'EM'), ('.', 'SF'), ('저', 'NP'), ('의', 'JKG'), ('이름', 'NNG'), ('은', 'JX'), ('홍길동', 'NNP'), ('이', 'VCP'), ('ㅂ니다', 'EM'), ('.', 'SF')]

    kukolex.morphs('안녕하세요. 저의 이름은 홍길동입니다.')
    # ['안녕', '하', '시', '어요', '.', '저', '의', '이름', '은', '홍길동', '이', 'ㅂ니다', '.']

    kukolex.pos('안녕하세요. 저의 이름은 홍길동입니다.')
    # ['NNG', 'XSA', 'EP', 'EM', 'SF', 'NP', 'JKG', 'NNG', 'JX', 'NNP', 'VCP', 'EM', 'SF']

    kukolex.nouns('안녕하세요. 저의 이름은 홍길동입니다.')
    # ['안녕', '저', '이름', '홍길동']