scarletcho

KoG2P

Korean grapheme-to-phone conversion in Python

KoLM

Korean text normalization and language preparation package for LM in Kaldi-based ASR system

prep4kaldi

Data preparation code for building Kaldi ASR system

runWord2vec

Wrapper of Gensim word2vec along with T-SNE visualization

hypernym-path-generation

Path-based hypernym prediction models in WordNet (WN18RR-hp)

evaluateFA

Evaluation script for a forced aligned TextGrid

naivebayes_cs124

A naive bayes classifier for text (as a group exercise from CS124 at Stanford)

subword-mikolov

An implementation of subword division algorithm proposed in T. Mikolov (2012).

comet-atomic-2020

iir

Machine Learning / Natural Language Processing / Information Retrieval

interpretability

nlp-with-pytorch

<파이토치로 배우는 자연어 처리>(한빛미디어, 2021)의 소스 코드를 위한 저장소입니다.

NNmnist

A simple neural network implementation for MNIST dataset

NNproject

An implementation of Artificial Neural Network from scratch (in MATLAB)

optimization

Implementation of 1st and 2nd order optimization (gradient descent and Newton's method)

pathlm_schema

Code for EMNLP 2020 paper `Connecting the Dots: Event Graph Schema Induction with Path Language Modeling`

pcaEigen

Implementation of PCA and Eigenvalue decomposition from scratch

poincare-embeddings

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

praatscripts

Useful praatscripts for audio data processing

project1

project2

Python-Lectures

IPython Notebooks to learn Python

scarletcho.github.io

tf-stanford-tutorials

This repository contains code examples for the course CS 20SI: TensorFlow for Deep Learning Research.

transformers-nli

transliteration

English to Korean Transliteration (영어-한글 표기 변환기)

WN18RR-hp

A filtered subset of hypernymy and instance hypernymy pairs from WN18RR (Dettmers et al., 2018) for hypernym prediction using taxonomy path generation.

word-embeddings-benchmarks

Package for evaluating word embeddings