-
Notifications
You must be signed in to change notification settings - Fork 182
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
微博新闻摘要数据测试集性能很差 #21
Comments
需要使用哪个数据训练一下,在测试呀。而且解码规则是不一样的,unilm那个为了保证效果,采用的beamsearch解码。这个项目是为了展示结果的多样性,采用的topk和topp解码。 并且,本项目的gpt2模型,我是随机初始化,并且训练轮数仅有5轮。unilm模型是预训练过,有继续再那个数据微调之后的结果。 |
谢谢大佬回复,针对您的回复,我再问细点:
|
回复2. 我写了一个beam search解码效果还可以,rouge能到40% |
请教一下有没有代码可以参考下呀 |
大佬请问有没有开源代码参考呢? |
大佬你好,我用https://github.com/YunwenTechnology/Unilm
提供的微博新闻摘要数据(从中随机挑选10000篇作为训练集,1000篇作为测试集)测试了下GPT2,发现rouge-1只有不到20%,而UniLM给出的结果有40.58%,请问这大概是什么原因?是GPT2的效果就是不好吗
The text was updated successfully, but these errors were encountered: