Heejin Do's repositories
SB_loss_PA
This repository is the implementation of the paper, "Score-balanced Loss for Multi-aspect Pronunciation Assessment" (Interspeech 2023).
multilingual-kd-pytorch
ICLR2019, Multilingual Neural Machine Translation with Knowledge Distillation
AES
Automatic Essay Scoring
aSTS-EI
This repository is the dataset of aSTS-EI, introduced in the paper, Aspect-based Semantic Textual Similarity for Educational Test Items (AIED 2024).
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
Automated-Essay--Scoring
Automatically Score essays using Deep Learning
bert
TensorFlow code and pre-trained models for BERT
BERT-Korean-Model
BERT with SentencePiece for Korean text
cross-prompt-trait-scoring
This repository contains the code used to produce the results from the paper Automated Cross-prompt Scoring of Essay Traits published in AAAI 2021.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
detect-gpt
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
EditEval
An instruction-based benchmark for text improvements.
expats
EXPATS: A Toolkit for Explainable Automated Text Scoring
flores
Facebook Low Resource (FLoRes) MT Benchmark
knowledge-distillation
PyTorch implementations of algorithms for knowledge distillation.
mt-dnn
Multi-Task Deep Neural Networks for Natural Language Understanding
muss
Code and models used in "MUSS Multilingual Unsupervised Sentence Simplification by Mining Paraphrases".
nea
Neural Essay Assessor: An Automated Essay Scoring System Based on Deep Neural Networks
PyTorch
Deep Learning Zero to All - Pytorch
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
trax
Trax — your path to advanced deep learning
word-embeddings-for-nmt
Supplementary material for "When and Why Are Pre-trained Word Embeddings Useful for Neural Machine Translation?" at NAACL 2018