Comments (8)
@yxuansu Perfect thanks for the effort. This will help me a lot. I will contact you if I have any issues :)
from simctg.
@yxuansu Perfect thanks for the effort. This will help me a lot. I will contact you if I have any issues :)
You are welcome. Please free feel to contact if you meet any problem :-)
from simctg.
Have you used simCTG on tasks like summarization ? After reading the paper I think simCTG can be adopted to tasks like text-summarization. Since simCTG was designed for open-ended generation how can I adopt it for text summarization ?
Any tips or advices ?
from simctg.
Have you used simCTG on tasks like summarization ? After reading the paper I think simCTG can be adopted to tasks like text-summarization. Since simCTG was designed for open-ended generation how can I adopt it for text summarization ?
Any tips or advices ?
Hi,
I definitely think SimCTG can be applied to tasks like summarization or translation. My advice is to follow the same procedure as described in the paper: (1) first using contrastive training to train you summarization model (e.g. BART or T5); (2) use contrastive search to generate the result.
For the contrastive training on encoder-decoder models, I recommend you to read this blog (https://zenn.dev/kwashizzz/articles/ml-simctg-contrastive-framework). They provide a good tutorial and code implementation on applying contrastive training on the T5 model. After contrastive training, you can refer to our tutorial (https://github.com/yxuansu/SimCTG/tree/main/SimCTGEncDec) on how to apply contrastive search to your trained model.
Please let me know if you have any further questions.
from simctg.
in your instructions do you apply diverse contrastive search ? if not any hints on how to implement it ?
Also what is the effect of beam_width ?
from simctg.
in your instructions do you apply diverse contrastive search ? if not any hints on how to implement it ?
Also what is the effect of beam_width ?
No, we did not implement the diverse contrastive search. I think you can easily adapt the code by yourself by referring to the details here (
SimCTG/document_generation/simctg.py
Line 135 in 9d294f7
Regarding the beam width, it does not affect that much as compared with \alpha, but I recommend you to try different values of beam width to see the performance difference.
from simctg.
I was training BART for summarization using simCTG on custom dataset, the model does not seem to improve after first epoch. I do not use external metrics such as rogue, I am using validation loss to save the best model. Any recommendations to stabilise the training and improve the performance ?
from simctg.
I was training BART for summarization using simCTG on custom dataset, the model does not seem to improve after first epoch. I do not use external metrics such as rogue, I am using validation loss to save the best model. Any recommendations to stabilise the training and improve the performance ?
Can I see the learning log of the MLE loss and contrastive loss of your training process?
from simctg.
Related Issues (20)
- 请问contrastive loss对生成的影响程度如何,应如何定义contrastive loss和生成的cross-entropy loss的权重大小? HOT 2
- Dialogue generation training with simctg library HOT 1
- fast_contrastive_search只支持batch_size=1吗 HOT 1
- about contrastive search HOT 1
- Typo in story_generation part HOT 1
- license file HOT 6
- Bloom Ai HOT 3
- about the repetition of the ground-turth HOT 3
- SimCTGT5和fast_contrastive_search相关问题(EncDecContrastiveDecodingOneStepFast) HOT 2
- Contrastive Training loss的部分疑惑 HOT 1
- Questions about Document Generation HOT 1
- Questions about evaluation metrics coherence and gen-ppl?
- About metric reproduction
- What's the difference between SimCTG and CnNT?
- Can you provide BartModel for SimCTG code?
- SimCTG BART training
- pip install error HOT 2
- Question about replicating the MAUVE scores HOT 3
- similar sentence generation HOT 2
- 关于fast_contrastive_search实现中新生成的token的embedding的理解(hv) HOT 6
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 simctg.