Comments (6)
Hi @dongguanting, this is how MAML does it. You can refer the MAML paper or other tutorials like AAAI21 MetaLearning Tutorial.
In short, for the inner update part, the model fine-tunes specific task i data based on original model parameter
The output update bp will calculate after all of the tasks' inner updates. The second-order derivative will make the model pay more attention to the transfer of knowledge between different tasks.
from vert-papers.
Hi @dongguanting, in fact, the whole logic can be found by analyzing the running script.
You can find MAML logic in forward_meta
function, both inner loop and outer loop.
You can also find ProtoNet in the forwad_wuq
function https://github.com/microsoft/vert-papers/blob/master/papers/DecomposedMetaNER/modeling.py#L125. We use a packaged nn.embedding
class EntityTypes
to memorize type embeddings.
from vert-papers.
Hi @iofu728, Thank you for your answer! But I still have another question which bothers me. I find that the model will backward twice during forward_meta function, namely inner update function and outer forward_wuqh. I think it may be related to MAML method, but why split into two processes to backward?
from vert-papers.
Hi, I also have similar question. Is there any parameter to control meta-learning? I want to reproduce the results of 1) Ours w/o MAML.
from vert-papers.
Hi @wjczf123, yeah, the code also supports full supervision mode(w/o MAML). You can set the use_supervise
argument to True
, which will call the forward_supervise
function instead of forward_meta
.
from vert-papers.
Nice! Thank you very much.
from vert-papers.
Related Issues (20)
- How to run CANNER code HOT 2
- This repo is missing important files
- How to deal with labels that don't appear in N-way labels HOT 1
- A question about meta-learning few-shot NER HOT 5
- A detailed question about meta-testing HOT 2
- The version of FewNERD HOT 9
- This repo is missing a license file HOT 1
- a experiment about meta-test HOT 8
- Error when running code of advpicker HOT 2
- Migration Problem of Code on Apple M1 Chip HOT 1
- CAN-NER 里的训练代码中pretrained_embed_path 应该放什么文件啊? HOT 1
- 请问 《Decomposed Meta-Learning for Few-Shot Named Entity Recognition》模型的训练时长多少 HOT 3
- The result of decoding BPE HOT 4
- cannot downlload models
- cannot download the models
- Obtaining Predicted NER Results for a Series of Sentences with DecomposedMetaNER HOT 3
- DecomposedMetaNER evaluate problem HOT 4
- Fail to reproduce the f1 score for dataset Cross-Dataset HOT 9
- Why my results are so poor? 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 vert-papers.