Ukjae Jeong
Ukjae Jeong
korean-spacing-model
한국어 문장 띄어쓰기(삭제/추가) 모델입니다. 데이터 준비 후 직접 학습이 가능하도록 작성하였습니다.
KR-BERT-SimCSE
Implementing SimCSE using KR-BERT
namuwiki-corpus
문장단위로 분절된 나무위키 데이터셋. Releases에서 다운로드 받거나, tfds-korean을 통해 다운로드 받으세요.
nori-clone
Standalone Nori (Korean Morphological Analyzer)
python-mecab
A repository to bind mecab for Python 3.5+. Not using swig nor pybind. (Not Maintained Now)
pytorch-bert
An implementation of BERT using PyTorch's TransformerEncoder
smaller-labse
Applying "Load What You Need: Smaller Versions of Multilingual BERT" to LaBSE
tfds-korean
A collection of Korean Text Datasets ready to use using Tensorflow-Datasets.
lightgbm-serving
A lightweight server for LightGBM
CLIP-self-attention-visualization
Plotting heatmaps with the self-attention of the [CLS] tokens in the last layer.