Comments (9)
We use back-translation to create paraphrases for unlabeled data and perform consistency training. You could use other ways to generate paraphrases.
from mixtext.
So I have to create paraphrases, right? In addition, When I look at the code, I find that only the first 100,000 pieces of data in the data set have been back translated. Do I not need to perform back translation for all the datasets?
from mixtext.
It depends on the size of the unlabeled data you are going to use. In this work, we used 100,000 unlabeled data, so we just did back translations on them, not the whole dataset.
from mixtext.
Sorry, I'm still a little confused.
When I test with:
python ./code/train.py --gpu 0,1 --n-labeled 10 \ --data-path ./data/yahoo_answers_csv/ --batch-size 2 --batch-size-u 4 --epochs 20 --val-iteration 1000 \ --lambda-u 1 --T 0.5 --alpha 16 --mix-layers-set 7 9 12 \ --lrmain 0.000005 --lrlast 0.0005
The number of unlabeled data per class seems to be 5,000. Do they add up to exactly 100,000?
from mixtext.
You could use up to 100,000
from mixtext.
10,000
from mixtext.
Anyway, the number of data you need to paraphrase only depends on the number of unlabeled data you are going to use.
from mixtext.
Are they one-to-one correspondence?
from mixtext.
one unlabeled data could be associated with multiple paraphrases. Please refer to the paper/codes for details.
from mixtext.
Related Issues (20)
- Loss function for supervised loss HOT 2
- tcmalloc: large alloc 44581601280 bytes HOT 1
- I want to know what 102 means HOT 5
- Can you provide all back translation data? HOT 7
- hyper-parameters HOT 1
- About args.val-iterations. HOT 1
- reproducing results for BERT baseline HOT 1
- How to use other models such as DistilBert or RoBerta? HOT 1
- About dataset construction HOT 1
- Changing the sequence length for BERT & performance on data with multi-class labels. HOT 3
- Parameter problem
- TypeError: init_weights() missing 1 required positional argument: 'module' HOT 1
- attention mask HOT 1
- How to use the method for bert ner task? HOT 1
- Not using entropy minimization loss in the final model? HOT 1
- KeyError: unlabeled_train_iter.next() HOT 4
- AttributeError: 'BertConfig' object has no attribute 'chunk_size_feed_forward' HOT 2
- yml file of environment
- 库的版本信息不明确,无法复现代码 HOT 1
- The pre-processed Yahoo Answer dataset HOT 2
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 mixtext.