hash2430's repositories
BERT_sentiment_classification
BERT-based binary sentiment classification + Byte-pair encoding (BPE) implemented from scratch.
French_EN_NMT
French to English neural machine translation trained on multi30k dataset.
Question_answering
This simple question answering model achieves F1 score of 80.56 on dev set of SQuAD
ai-deadlines
:alarm_clock: AI conference deadline countdowns
AwesomeKorean_Data
ํ๊ตญ์ด ๋ฐ์ดํฐ ์ธํธ ๋งํฌ
DistilKoBERT
Distillation of KoBERT from SKTBrain (Lightweight KoBERT)
emotiontts_open_db
์์ฑDB ๊ณต๊ฐ
Episodic-DG
This is the repo for the paper "Episodic Training for Domain Generalization" https://arxiv.org/abs/1902.00113
GoEmotions-Korean
Korean version of GoEmotions Dataset ๐๐ข๐ฑ
KoBERT
Korean BERT pre-trained cased (KoBERT)
KoBERT-nsmc
Naver movie review sentiment classification with KoBERT
KoELECTRA
Pretrained ELECTRA Model for Korean
kor_pratrain_LM
https://ailabs.enliple.com/
korean-hate-speech
Korean HateSpeech Dataset
ML-Interview
Resources I used for ML Engineer, Applied Scientist and Quant Researcher interviews.
nlp-startups
๊ตญ๋ด ์์ฐ์ด ์ฒ๋ฆฌ ๊ธฐ์ ์ ์ฐ๊ตฌ ๋ฐ ๊ฐ๋ฐํ๋ ์คํํธ์ ๋ชฉ๋ก
nlpaug
Data augmentation for NLP
sacred
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.