Comments (2)
qibinc
commented on September 2, 2024
Hi @ga2006084851 ,
- The latter.
- 在我们的这篇工作和 code 中没有办法限制 decode 出来的字数，不过基本也都跟训练集的 description 长度差不多。可以在 beam search decode 的时候强行在某个 timestep 取 (end of sequence)，但会影响效果。我觉得应该有一些文献尝试解决过这个问题，但效果应该有限，毕竟不能和训练集中的长度相差太多。如果训练集中大都是 100，而你需要 30，这样可以考虑用其他数据训练一个 summarization 的模型，对生成的过长的 description 做后处理。或者如果原来的训练数据充足，建议直接丢掉过长的 training sample.
Hope this helps!
from kobe.
ga2006084851
commented on September 2, 2024
我明白了，真的感謝您的幫忙!!!
from kobe.
Related Issues (20)
- Issue with evaluating model with beam search HOT 4
- Named entity to match product title with knowledge graph HOT 2
- Explaination about your preprocessed data HOT 3
- Failed to download the processed training data HOT 1
- detail user category HOT 1
- At the end of the run, the bleu score can no longer be improved at around 6. HOT 5
- Is there any dataset in English? HOT 1
- how long does the training process last?Could u please provide the training result? HOT 3
- How do you build the fact file in raw data? HOT 8
- Good name! HOT 1
- inference HOT 2
- 请问怎么在自己的数据集上做finetune和推理？ HOT 4
- Error when preprocessing dataset HOT 1
- Why did you delete bi-attention code? HOT 2
- English language dataset HOT 1
- 关于模型的generate的API试用问题 HOT 1
- ignore this issue
- 关于24-V2训练
- WandB Link?
- 请问有图生文的部分吗
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 kobe.