shelleyyyyu

Adaptive_Multi-curricula_Learning_for_Dialog

The codebase for "Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation" (Cai et al., AAAI 2020)

bert

TensorFlow code and pre-trained models for BERT

BERT-1

a simple yet complete implementation of the popular BERT model

Bert_QuatE

bookcorpus

Crawl BookCorpus

cgec

clustering

CommonsenseStoryGen

Implementation for paper "A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation"

CTC-Report

fed_gec

shelleyyyyu/fed_gec

shelleyyyyu/Adaptive_Multi-curricula_Learning_for_Dialog

The codebase for "Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation" (Cai et al., AAAI 2020)

shelleyyyyu/bert

TensorFlow code and pre-trained models for BERT

shelleyyyyu/BERT-1

a simple yet complete implementation of the popular BERT model

shelleyyyyu/Bert_QuatE

shelleyyyyu/cgec

shelleyyyyu/clustering

shelleyyyyu/CommonsenseStoryGen

Implementation for paper "A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation"

shelleyyyyu/CTC-Report

shelleyyyyu/data_augmentation_auto

shelleyyyyu/data_augmentation_rule

shelleyyyyu/Dialogue

shelleyyyyu/dssm

DSSM and Multi-View DSSM

shelleyyyyu/few_shot

shelleyyyyu/gector

Official implementation of the papers "GECToR – Grammatical Error Correction: Tag, Not Rewrite" (BEA-20) and "Text Simplification by Tagging" (BEA-21)

shelleyyyyu/gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

shelleyyyyu/IOI

Tensorflow implementation for IOI model

shelleyyyyu/KG_BERT

shelleyyyyu/learning-data-manipulation

shelleyyyyu/military_data

shelleyyyyu/mlmlm

shelleyyyyu/MuCGEC

MuCGEC中文纠错数据集及文本纠错SOTA模型开源；Code & Data for our NAACL 2022 Paper "MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction"

shelleyyyyu/MultiTurnResponseSelection

This repo contains our ACL 2017 paper data and source code

shelleyyyyu/PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

shelleyyyyu/QuatE

Pytorch implementation of Quaternion Knowledge Graph Embeddings.

shelleyyyyu/RecBole

A unified, comprehensive and efficient recommendation library

shelleyyyyu/sentence-transformers

Sentence Embeddings with BERT & XLNet

shelleyyyyu/transE_tf

shelleyyyyu/TtT

code for ACL2021 paper "Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction"

shelleyyyyu/UIE

Unified Structure Generation for Universal Information Extraction