thunlp / plmpapers Goto Github PK
View Code? Open in Web Editor NEWMust-read Papers on pre-trained language models.
License: MIT License
Must-read Papers on pre-trained language models.
License: MIT License
Thanks! This is a great resource. Could you add our recent MultiFiT (Eisenschlos et al., EMNLP 2019) that extends ULMFiT for multilingual applications to the diagram?
For relatively new conference papers like ICRL2020, are you sure about the quality? I think there are a lot of articles recently added. After all, the title is a must-read thesis. I hope to control it and only keep the essence.thanks
Hi,
We have released the code of TinyBERT here (https://github.com/huawei-noah/Pretrained-Language-Model/tree/master/TinyBERT). Could you please add it?
Thanks
Just a small typo. LXMBERT should be LXMERT in the diagram.
DistilBERT is proposed by Hugging Face and implemented in pytorch-transformers. I think this work is worth adding to the repo.
You might consider adding context2vec, which was one of the predecessors to ELMo and inspired much of the work on LM pre-training: https://www.aclweb.org/anthology/K16-1006.pdf
Hi,
Wonderful paper list! Could you please update the new link (https://arxiv.org/pdf/1909.10351v2.pdf) of TinyBERT?
Thanks
GPT到BERT中的BidirectionalLM是指双向LSTM吗? 如果是的话,是不是应该 ELMo才是BidirectionalLM,然后指向BERT啊。
BERT和GPT都是Transformer,GPT指向BERT是Transformer。
Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel
https://arxiv.org/abs/1908.11775
Another perspective to understand the attention formulation of Transformer.
Hi,
I'm the first author of a paper mentioned in this list, "Thieves on Sesame Street! Model Extraction of BERT-based APIs". Firstly, thanks so much for the mention!
I feel the paper might be more appropriate under the Knowledge Distillation & Model Compression section or the Analysis section, since it's not really a new model.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.