J-Seo

Korean-CommonGen

[Findings of NAACL2022] A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and Evaluation

KommonGen

한국어 생성 모델의 상식 추론을 위한 KommonGen 데이터셋입니다.

BDC103_IR

This repository is practice for Big Data and Information Retrieval class.

KoGPT2_Finetuning_for_Classification

Finetuning for Korean Sentiment analysis 'NSMC'

SRLev-BIH

SRLev-BIH: 한국어 일반 상식 추론 및 생성 능력 평가 지표

class2019Fall-1

EmotionX-2019

NLG_metrics

NLG Evaluation Metrics

sgg

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"

text_summarization

find a middle point 'chat bot' <-> 'x' <-> 'translation'

AWS

class2019Spring

CommonGen

A Constrained Text Generation Challenge Towards Generative Commonsense Reasoning

CSAT_data_analysis

Pi_ville_project

CSAT_Text_Generation

Pi_ville_project, creating the text with RNN, LSTM, and Transformer

CSAT_Vocab

Pi_ville_project

demo-self-driving

Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.

J-Seo.github.io

KULLM

구름(KULLM): 고려대학교에서 개발한, 한국어에 특화된 LLM

news_recommendation

predict_bicycle_with_r

Predicting public bicycle usage 2019 based on time and weather variables with R

Pytorch_NLG

renew_csat_project

improve data quality, learning model, and others for preparing report

subword-nmt

Subword Neural Machine Translation based on rsennrich, but include feature to deal with a sentence already tokenized.

Udacity_Image_classifier

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.

wikiextractor

A tool for extracting plain text from Wikipedia dumps