LexRank for Korean

Text summarization using LexRank algorithm for Korean. Click here to see how to install KoNLPy properly. older version using TextRank.

See related paper: lexrankr: LexRank 기반 한국어 다중 문서 요약

Installation

pip install lexrankr

Usage

from __future__ import print_function
from lexrankr import LexRank

lexrank = LexRank()  # can init with various settings
lexrank.summarize(your_text_here)
summaries = lexrank.probe(num_summaries)  # `num_summaries` can be `None` (using auto-detected topics)
for summary in summaries:
    print(summary)

Test

python -m tests.test