L0Z1K / para-Kor
Create paraphrasing korean sentence with GPT-3
☆34Updated last year
Related projects ⓘ
Alternatives and complementary repositories for para-Kor
- Korean Math Word Problems☆57Updated 2 years ago
- Adversarial Test Dataset for Korean Multi-turn Response Selection☆34Updated 2 years ago
- bpe based korean t5 model for text-to-text unified framework☆63Updated 7 months ago
- Dataset of Korean Threatening Conversations☆70Updated 2 years ago
- 🤗 최소한의 세팅으로 LM을 학습하기 위한 샘플코드☆57Updated last year
- Character-level Korean ELECTRA Model (음절 단위 한국어 ELECTRA)☆53Updated last year
- KOLD: Korean Offensive Language Dataset☆78Updated 2 years ago
- kogpt를 oslo로 파인튜닝하는 예제.☆23Updated 2 years ago
- ☆26Updated 2 years ago
- 한국어 노이즈 생성을 위한 라이브러리입니다.☆18Updated last year
- ELECTRA기반 한국어 대화체 언어모델☆54Updated 3 years ago
- Kobart model on Huggingface transformers☆63Updated 2 years ago
- ☆32Updated last year
- KoBART chatbot☆47Updated 3 years ago
- This repository contains Korean Hate Speech dataset for paper, "K-MHaS: A Multi-label Hate Speech Detection Dataset in Korean Online News…☆40Updated 6 months ago
- ☆57Updated 10 months ago
- APEACH: Attacking Pejorative Expressions with Analysis on Crowd-generated Hate Speech Evaluation Datasets☆75Updated last year
- Korean Light Weight Language Model☆30Updated last year
- huggingface를 이용하여 downstream task 수행하기☆64Updated 2 years ago
- BERTScore for Korean☆73Updated 9 months ago
- 나무위키덤프에서 정제된 텍스트를 얻기 위한 NamuwikiExtractor☆16Updated 2 years ago
- KorQuAD Korean domain Question Generation module based on KoBART☆28Updated 2 years ago
- ☆31Updated 11 months ago
- Yet another python binding for mecab-ko☆80Updated last year
- For the rlhf learning environment of Koreans☆23Updated last year
- State-of-the-art Retrieval Model implementing "Dense Passage Retrieval for Open-Domain Question Answering" with Korean Dataset.☆9Updated 2 years ago
- 한국어 T5 모델☆46Updated 2 years ago
- [Findings of NAACL2022] A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and Evaluation☆28Updated last year
- The code and models for "An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks" (AACL-IJCNLP 2020)☆116Updated 4 years ago
- A utility for storing and reading files for Korean LM training 💾☆36Updated 10 months ago