This repository is to collect BERT related resources.
AD: a repository for graph convolutional networks at https://github.com/Jiakui/awesome-gcn (resources for graph convolutional networks (图卷积神经网络相关资源)).
Papers:
arXiv:1810.04805, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
, Authors: Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova
arXiv:1812.03593, SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering, Authors: Chenguang Zhu, Michael Zeng, Xuedong Huang
arXiv:1901.02860, Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context, Authors: Zihang Dai, Zhilin Yang, Yiming Yang, William W. Cohen, Jaime Carbonell, Quoc V. Le and Ruslan Salakhutdinov.
arXiv:1901.04085, Passage Re-ranking with BERT, Authors: Rodrigo Nogueira, Kyunghyun Cho
arXiv:1902.02671, BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning, Authors: Asa Cooper Stickland, Iain Murray
arXiv:1904.02232, BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis, Authors: Hu Xu, Bing Liu, Lei Shu, Philip S. Yu, [code]
Github Repositories:
official implement:
google-research/bert, officical TensorFlow code and pre-trained models for BERT ,
dmlc/gluon-nlp, Gluon + MXNet implementation that reproduces BERT pretraining and finetuning on GLUE benchmark, SQuAD, etc,
dbiir/UER-py, UER-py is a toolkit for pre-training on general-domain corpus and fine-tuning on downstream task. UER-py maintains model modularity and supports research extensibility. It facilitates the use of different pre-training models (e.g. BERT), and provides interfaces for users to further extend upon.
BrikerMan/Kashgari, Simple, Keras-powered multilingual NLP framework, allows you to build your models in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS) and text classification tasks. Includes BERT, GPT-2 and word2vec embedding.
thunlp/ERNIE, Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities", imporove bert with heterogeneous information fusion.
PaddlePaddle/LARK, LAnguage Representations Kit, PaddlePaddle implementation of BERT. It also contains an improved version of BERT, ERNIE, for chinese NLP tasks. BERT 的中文改进版 ERNIE,
zihangdai/xlnet, XLNet: Generalized Autoregressive Pretraining for Language Understanding,
kimiyoung/transformer-xl, Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context, This repository contains the code in both PyTorch and TensorFlow for our paper.
PaddlePaddle/ERNIE, An Implementation of ERNIE For Language Understanding (including Pre-training models and Fine-tuning tools) BERT 的中文改进版 ERNIE,
pytorch/fairseq, Facebook AI Research Sequence-to-Sequence Toolkit written in Python. RoBERTa: A Robustly Optimized BERT Pretraining Approach,
facebookresearch/SpanBERT, Code for using and evaluating SpanBERT.
, This repository contains code and models for the paper: SpanBERT: Improving Pre-training by Representing and Predicting Spans.,
请发表评论