Name: Myeong-Ha Hwang
Type: User
Company: Korea Electric Power Research Institute(KEPRI)
Bio: A.I. Researcher
(Explainable AI(XAI), Large Language Model(LLM), Knowledge Graph(KG), Text Mining, Natural Language Processing(NLP))
Blog: https://sites.google.com/site/raphael900929/
Myeong-Ha Hwang's Projects
DeepLearning_Lecture 2019 in Industrial Engineering at KAIST
Explainable recommendation via interpretable feature mapping
Tensorflow implementation for prodLDA and NVLDA.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
GoogleBERT(Multilingual) + KorQuAD
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Bicluster Example in R
Document Table -> Parsing the contents column -> LDA(1,1) -> Construct Topic Table
Discovering New Intents with Deep Aligned Clustering (AAAI 2021)
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.
A knowledge graph and a set of tools for drug repurposing
Database
A database of paths that represent the mechanism of action from a drug to a disease in an indication.
Here we propose a novel end-to-end approach named DSGAT for drug-side effect frequency prediction by using graph attention networks (GAT) . DSGAT learns the drug representation from the molecular graph, and has the ability to predict the frequencies of side effects for cold start drugs that do not appear in the training data.
DSTC 11 Track 2: Intent Induction from Conversations for Task-Oriented Dialogue
2020 패스트캠퍼스 추천시스템 A to Z
Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️♂️
Hetionet: an integrative network of disease
The GitHub repository for the paper "Informer" accepted by AAAI 2021.
코딩셰프의 3분 딥러닝, 케라스맛
📖 Korean NLU Benchmark
KoAlpaca: Korean Alpaca Model based on Stanford Alpaca (feat. LLAMA and Polyglot-ko)
Korean BERT pre-trained cased (KoBERT)
Let's use Korean BERT easily :)
Korean BERT model using character tokenizer
Source codes and example data for the LDA-based scRNA-seq analysis workflow
Inference code for LLaMA models