metadata

license: cc-by-sa-4.0
datasets:
  - kubota/defamation-japanese-twitter
language:
  - ja
pipeline_tag: text-classification
widget:
  - text: お前のことを殺すぞ
  - text: 本当に不細工だなぁ
  - text: あの人は殺人を犯した犯罪者らしい

luke-large-defamation-detection-japanese

日本語誹謗中傷検出器

This model is a fine-tuned version of studio-ousia/luke-japanese-large for the Japanese language finetuned for automatic defamation detection.

The original foundation model was finetuned on a balanced dataset created by unifying two datasets:

DefamationJapaneseYouTube : TBA

Labels:
0 -> "中傷性のない発言"
1 -> "脅迫的な発言"
2 -> "侮蔑的な発言"
3"-> "名誉を低下させる発言"

Example Pipeline

# !pip install transformers==4.26 sentencepiece
from transformers import pipeline
pipe = pipeline(model="kubota/luke-large-defamation-detection-japanese")
pipe("あの人は殺人を犯した犯罪者らしい")

[{'label': '名誉を低下させる発言', 'score': 0.8889994621276855}]

Training Scripts

Licenses

The finetuned model with all attached files is licensed under CC BY-SA 4.0, or Creative Commons Attribution-ShareAlike 4.0 International License.