Comments (2)
If you have manually checked several examples of augmented data and their labels and those are correct, then your code for generating the augmented data is probably correct.
I am not sure about how EDA affects the performance of BERT. One reason I could think of that might hurt the performance is if BERT already has the ability to do well on TREC and SST (which it probably does), i.e., there is little or no overfitting on BERT, then introducing some augmentations might actually hurt its performance. To be conservative, you can try using a really low alpha parameter (0.05 or 0.03).
Sorry I can't be more helpful on this occasion. If you find that EDA does not do well versus long or short texts, and want to report some results on that, I'm happy to modify the readme so that others know.
from eda_nlp.
Thanks very much for your reply. I will do more experiments based on BERT and give feedback if there are new discoveries.
from eda_nlp.
Related Issues (20)
- Confirmation abt data augmentation HOT 4
- Possibility of masking some tokens? HOT 1
- What is the role of label here?
- empty range for randrange() HOT 2
- random_insertion should take stop words into account HOT 2
- BERT + EDA ? HOT 2
- performance gain of each eda method HOT 2
- A little suggestion about error exception
- Mechanism to choose between EDA tasks HOT 2
- Run augmentation on my dataset, unsure how to procceed. HOT 1
- Semi-supervised HOT 1
- Languages supported HOT 1
- Something about the best parameters HOT 1
- ValueError: empty range for randrange() (0,0, 0) HOT 4
- Random Insertion can't insert word into the last position ?
- Supported languages.
- Need Code for paper "Good-Enough Example Extrapolation"
- Liencese of this repo HOT 1
- Tips for Non-English Augmentation
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 eda_nlp.