Beomi/KcELECTRA
π€ Korean Comments ELECTRA: νκ΅μ΄ λκΈλ‘ νμ΅ν ELECTRA λͺ¨λΈ
This project provides a specialized Korean language AI model designed to understand the nuances of online comments. It takes raw, often messy, Korean user-generated text, like social media comments or forum posts, and processes it to enable more accurate analysis. It's intended for anyone who needs to make sense of informal, conversational, and typo-ridden Korean text, such as social media analysts, customer feedback managers, or market researchers.
261 stars. No commits in the last 6 months.
Use this if you need to analyze highly informal, user-generated Korean text like online comments, where standard language models might struggle with slang, typos, and conversational patterns.
Not ideal if your primary task involves analyzing formal, well-structured Korean text from sources like news articles, books, or official documents, as general corpus models might perform better there.
Stars
261
Forks
26
Language
—
License
MIT
Category
Last pushed
Nov 07, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Beomi/KcELECTRA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
SKTBrain/KoBERT
Korean BERT pre-trained cased (KoBERT)
monologg/KoELECTRA
Pretrained ELECTRA Model for Korean
monologg/KoBERT-Transformers
KoBERT on π€ Huggingface Transformers π€ (with Bug Fixed)
VinAIResearch/PhoBERT
PhoBERT: Pre-trained language models for Vietnamese (EMNLP-2020 Findings)
KB-AI-Research/KB-ALBERT
KBκ΅λ―Όμνμμ μ 곡νλ κ²½μ /κΈμ΅ λλ©μΈμ νΉνλ νκ΅μ΄ ALBERT λͺ¨λΈ