Skip to content
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

怎么训练? #13

Open
g1kyne opened this issue May 5, 2022 · 8 comments
Open

怎么训练? #13

g1kyne opened this issue May 5, 2022 · 8 comments

Comments

@g1kyne
Copy link

g1kyne commented May 5, 2022

您好,想问下这份代码应该怎么进行训练?没有看到类似训练代码的文件

@simba0626
Copy link
Collaborator

感谢您的关注,
本方法是个pipeline方法,不是端到端方法,所以不太容易看出训练代码。

看您关注的是哪一部分了,Skeleton解析训练代码:https://github.com/nju-websoft/SPARQA/tree/master/code/parsing/models/fine_tuning_based_on_bert
词汇级语义匹配代码:https://github.com/nju-websoft/SPARQA/tree/master/code/grounding/ranking/path_match_nn

如有疑问,请您继续留言
感谢

@lys-github
Copy link

“SPARQA also provides a tool of parsing. The input is a question. The output is the skeleton of the question. ”
请问能否运行得到一个新问句的Ungrounded Query呢?应该怎么运行呢?

@simba0626
Copy link
Collaborator

您好,您可以看看这个文件下面的函数https://github.com/nju-websoft/SPARQA/blob/master/code/parsing/query_graph_generator.py
Skeleton和Ungrounded Query运行例子

感谢关注

@lys-github
Copy link

lys-github commented May 9, 2022 via email

@simba0626
Copy link
Collaborator

lys您好,抱歉刚才回答有误,您可以关注一下SPARQA更新版:https://github.com/nju-websoft/SkeletonKBQA,这个是在全集上(27639)运行的

@lys-github
Copy link

lys-github commented May 10, 2022 via email

@lys-github
Copy link

lys-github commented May 19, 2022 via email

@simba0626
Copy link
Collaborator

simba0626 commented May 20, 2022 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants