tomohideshibata / bert-related-papers Goto Github PK
View Code? Open in Web Editor NEWBERT-related papers
BERT-related papers
For Multi-Modal section:
VinVL: Revisiting Visual Representations in Vision-Language Models
12-in-1: Multi-Task Vision and Language Representation Learning
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
XGPT: Cross-modal Generative Pre-Training for Image Captioning
InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
And for Downstream task section:
CAPT: Contrastive Pre-Training for Learning Denoised Sequence Representations
Model Compression:
Playing Lottery Tickets with Vision and Language
https://arxiv.org/pdf/2104.11832.pdf
Hi,
Thank you for maintaining this awesome repo for all BERT-related papers. I came across this repo and found it quite helpful. I would like to expect it keep growing and updated!
I would like to suggest you to add two recent BERT-related papers from our group to your repo to make it even more comprehensive. Here are the two papers:
[1] GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension. (ICML2019 WS)
[2] Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation.
Thank you for the great work!
DirectProbe: Studying Representations without Classifiers
https://www.aclweb.org/anthology/2021.naacl-main.401/
Hi ,
I'm Kalyan, PhD candidate working in biomedical NLP. Here is the link for the latest survey paper on transformer based pretrained language models in biomedical NLP.
https://arxiv.org/abs/2105.00827
Can you please include this paper also in the list of survey papers? @tomohideshibata
Hi, I'd like to request adding our paper on the calibration of BERT (and RoBERTa) to this repo: https://arxiv.org/abs/2003.07892
Please add a new ACL2022 probing paper: https://aclanthology.org/2022.acl-long.75/
Thanks!
Inside BERT:
Model Compression:
Multi-Modal
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.