chan0park Goto Github PK

11747-nn4nlp

automatic-emailing-md

Built to automatically send markdown file to email in HTML format

blm-emotions

Official code and data of the paper "An Analysis of Emotions and the Prominence of Positivity in #BlackLivesMatter Tweets"

blogs

chan0park.github.io

Personal Webpage

distro

Torch installation in a self-contained folder

emotion-classification

glove-python

Toy Python implementation of http://www-nlp.stanford.edu/projects/glove/

hindi-tokenizer

This is a package in Python which implements a tokenizer, stemmer for Hindi language

hjerson

Hjerson: An Open Source Tool for Automatic Error Classification of Machine Translation Output

how-i-extracted-ted-talks-for-parallel-corpus-

lightgbm

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

long-summarization-1

Resources for the NAACL 2018 paper "A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents"

lowresource-nlp-bootcamp-2020

The website for the CMU Language Technologies Institute low resource NLP bootcamp 2020

mosesdecoder

Moses, the machine translation system

mucoco

Official Code for the paper: "Controlled Text Generation as Continuous Optimization with Multiple Constraints"

multilingual-affective-analysis

nlg-eval

Evaluation code for various unsupervised automated metrics for Natural Language Generation.

node2vec-by-ecc

normvio

Code and data for "Detecting Community Norm Violations in Online Conversations" (Park et al., 2021)

npmt

Towards Neural Phrase-based Machine Translation

opennmt-py

Open Source Neural Machine Translation in PyTorch

pconmt

Implementation of "Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation" (Park and Tsvetkov, 2019)

seq2seq-con

Implementation of "Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs"

stopwords-ko

Korean stopwords collection

talkup

the TalkUp data and the AMT annotation UI used to create the data set

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

vadersentiment

VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.

video-annotation-tool

voynaslov