j-seo Goto Github PK
Name: JaehyungSeo
Type: User
Company: Korea Univ
Bio: PH.D candidate in Computer Science at Korea University (NLP & AI Lab). Interested in Natural Language Generation and Commonsense Reasoning.
Location: Seoul, Korea
Name: JaehyungSeo
Type: User
Company: Korea Univ
Bio: PH.D candidate in Computer Science at Korea University (NLP & AI Lab). Interested in Natural Language Generation and Commonsense Reasoning.
Location: Seoul, Korea
This repository is practice for Big Data and Information Retrieval class.
A Constrained Text Generation Challenge Towards Generative Commonsense Reasoning
Pi_ville_project
Pi_ville_project, creating the text with RNN, LSTM, and Transformer
Pi_ville_project
Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.
Code for the paper "You Truly Understand What I Need : Intellectual and Friendly Dialogue Agents grounding Knowledge and Persona" which is accepted to EMNLP 2022 (Findings)
KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models
Finetuning for Korean Sentiment analysis 'NSMC'
한국어 생성 모델의 상식 추론을 위한 KommonGen 데이터셋입니다.
[Findings of NAACL2022] A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and Evaluation
구름(KULLM): 고려대학교에서 개발한, 한국어에 특화된 LLM
NLG Evaluation Metrics
A Situational Conversation-Based English Education Platform
Predicting public bicycle usage 2019 based on time and weather variables with R
improve data quality, learning model, and others for preparing report
Train Scene Graph Generation in PyTorch 1.2 or newer with improved zero and few-shot generalization. Paper: "Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation"
SRLev-BIH: 한국어 일반 상식 추론 및 생성 능력 평가 지표
Subword Neural Machine Translation based on rsennrich, but include feature to deal with a sentence already tokenized.
find a middle point 'chat bot' <-> 'x' <-> 'translation'
Image_classifier: Using 102 Flowers data, model classifies the flower images where they belong among 102 groups. train.py & predict.py: Users can train the model selecting some hyper-parameters and activation function etc... and check model performance calling predict.py.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.