Stars
Dataset and codes for identifying sentence-level discourse elements in Chinese argumentative student essays.
Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017
Data augmentation for NLP, presented at EMNLP 2019
"Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness" (NeurIPS 2020).
Toolbox for OCR post-correction
Modify Chinese text, modified on LaserTagger Model. 文本复述，基于lasertagger做中文文本数据增强。
PyTorch implementation of Contrastive Learning methods
Create and modify Word documents with Python
A Chinese argumentative student essay dataset for Organization Evaluation and Discourse Element Identification
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning
A dataset of 200k English plaintext jokes.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
BERT-CCPoem is an BERT-based pre-trained model particularly for Chinese classical poetry
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Multilingual Sentence & Image Embeddings with BERT
A curated list of Machine Learning Surveys, Tutorials and Books.
mirror of dongxiexidian/Chinese
Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)
《可解释的机器学习--黑盒模型可解释性理解指南》，该书为《Interpretable Machine Learning》中文版
List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.
This repository contains the the code from "Globally Coherent Text Generation with Neural Checklist Models" by Chloe Kiddon, Luke Zettlemoyer, and Yejin Choi