KWJA: Kyoto-Waseda Japanese Analyzer

KWJA is a Japanese language analyzer based on pre-trained language models. KWJA performs many language analysis tasks, including:

• Typo correction
• Tokenization
• Morphological analysis
• Named entity recognition
• Dependency parsing
• PAS analysis
• Coreference resolution
• Discourse relation analysis
• etc.

Requirements

• Python: 3.9+
• Dependencies: See pyproject.toml.

Getting Started

Install KWJA with pip:

$ pip install kwja

Perform language analysis with the kwja command (the result is in the KNP format):

# Analyze a text
$ kwja --text "月が綺麗ですね。死んでもいいわ。"

# Analyze a text file
$ kwja --file path/to/file.txt

Usage from Python

Make sure you have kwja command in your path:

$ which kwja
/path/to/kwja

Install rhoknp:

$ pip install rhoknp

Perform language analysis with the kwja instance:

from rhoknp import KWJA
kwja = KWJA()
analyzed_document = kwja.apply("月が綺麗ですね。死んでもいいわ。")

Citation

@InProceedings{植田2022,
  author    = {植田 暢大 and 大村 和正 and 児玉 貴志 and 清丸 寛一 and 村脇 有吾 and 河原 大輔 and 黒橋 禎夫},
  title     = {KWJA：汎用言語モデルに基づく日本語解析器},
  booktitle = {第253回自然言語処理研究会},
  year      = {2022},
  address   = {京都},
}