davidie's repositories
AGGCN
Attention Guided Graph Convolutional Networks for Relation Extraction (authors' PyTorch implementation for the ACL19 paper)
albert_zh
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
ATLOP
Source code for paper "Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling", AAAI 2021
AwesomeMRC
This repo is our research summary and playground for MRC. More features are coming.
biaffine-ner
Named Entity Recognition as Dependency Parsing
BLINK
Entity Linker solution
CasRel-pytorch-reimplement
Pytorch reimplement of the paper "A Novel Cascade Binary Tagging Framework for Relational Triple Extraction" ACL2020. The original code is written in keras.
Chinese-BERT-wwm
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
Chinese-PreTrained-XLNet
Pre-Trained Chinese XLNet（中文XLNet预训练模型）
CLEVE
Source code for ACL 2021 paper "CLEVE: Contrastive Pre-training for Event Extraction"
CLUE
中文任务基准测评 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
DeepLearningExamples
FasterTransformer
DeepNER
天池中药说明书实体识别挑战冠军方案；中文命名实体识别；NER; BERT-CRF & BERT-SPAN & BERT-MRC；Pytorch
dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.
DocEE
A toolkit for document-level event extraction, containing some SOTA model implementations.
fairseq
RoBERTa代码在examples/roberta - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
FewShotTagging
Code for ACL2020 paper: Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
FreeLB
Adversarial Training for Natural Language Understanding
hnswlib
Header-only C++/python library for fast approximate nearest neighbors
NeZha_Chinese_PyTorch
NEZHA: Neural Contextualized Representation for Chinese Language Understanding
NLPer-Arsenal
收录NLP相关竞赛经验贴（当前赛事、往期赛事、训练赛）、NLP会议时间、常用自媒体、GPU推荐等，持续更新中
QA-Survey
北航大数据高精尖中心研究团队对问答系统的调研。包括基于知识图谱的问答系统（KBQA）和基于文本的问答系统（TextQA），每类系统分别对学术界和工业界进行调研。
simple_tensorflow_serving
Generic and easy-to-use serving service for machine learning models
t5-pegasus-chinese
基于GOOGLE T5中文生成式模型的摘要生成/指代消解，支持batch批量生成，多进程
transformers
tensorflow版本实现了可直接调用的BERT/XLNET/RoBERTa等模型 - 🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
UER-py
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
xf_event_extraction2020Top1
科大讯飞2020事件抽取挑战赛第一名解决方案&完整事件抽取系统