Comments (3)
Is that LSRA combines multi-head attention and conv in a multi-branch manner, but ConvBert integrates conv into transformer blocks?
if the answer is yes. what are the pros and cons of the above two methods? Do you have experiments?
Thanks a lot!!!
from convbert.
Hi @yuanenming , Thanks for your interest.
LSRA is for machine translation and abstractive summarization. They are combining dynamic conv and multi-head attention in a two-branch manner.
ConvBERT is a pre-training based model that can be fine-tuned on downstream tasks like sentence classification. We also propose a novel span-based dynamic convolution operator and combine it with the self-attention to form the mixed-attention block.
Experiments comparing span-based dynamic conv and dynamic conv can be found in Section 4.3 Table 2 in our paper.
You can find that our span-based dynamic conv is better than dynamic conv in this pre-training based model setting. But it's hard to directly compare LSRA with ConvBERT.
from convbert.
Thank you for your timely reply!
I will close this issue.
from convbert.
Related Issues (20)
- 用自己的数据预训练 各种nah loss 问题 HOT 3
- 关于mixed-attention推理速度的问题 HOT 2
- 请问你提供的预训练模型是中文预训练模型 还是英文 是基于什么进行训练的 细节可以稍微介绍下吗 HOT 1
- 请问有pytorch版本发布吗? HOT 1
- The exact English pretraining data and Chinese pretraining data that are exact same to the BERT paper's pretraining data.
- Train on GPU instead of TPU - differnt distribution strategies HOT 2
- Training on multiple GPUs for BASE or LARGE Models HOT 2
- Where is the chinese convbert model?
- 请问有计划开源中文的模型吗 HOT 1
- Please update your citation bib HOT 1
- Is ConvBertModel autoregressive?
- UnboundLocalError: local variable 'seq_length' referenced before assignment
- 请问使用tpu还是gpu训练 HOT 7
- Pytorch version HOT 2
- 预测性能 HOT 4
- 疑惑 HOT 1
- 关于预训练的问题 HOT 1
- span light conv疑惑 HOT 1
- 这个预训练代码不就是ELECTRA那套? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from convbert.