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

请教问答系统,期待回复!感谢感谢! #2

Open
buling13 opened this issue Jun 24, 2024 · 8 comments
Open

请教问答系统,期待回复!感谢感谢! #2

buling13 opened this issue Jun 24, 2024 · 8 comments

Comments

@buling13
Copy link

您好,请问问答系统的实现分类器模型训练是否缺少__label__文件

@XuekaiChen
Copy link
Owner

是的,标签文件并未放上去,若想自己通过fasttext分类器简单训练,可参照以下格式自行编写训练集:

__label__greet 打扰 一下 __label__bot what your name ? __label__bot 你 是 机器人 吗 __label__bot 你 的 名字 ? __label__greet 你好 __label__greet hey __label__goodbye 忙 事情 去 了 __label__bot 你 叫 什么 名字 啊 __label__bot 你 到底 是 哪个 __label__goodbye 回见

@buling13
Copy link
Author

buling13 commented Jun 24, 2024 via email

@XuekaiChen
Copy link
Owner

自己的数据集需要按照本体在query_graph.py等代码里调整实体和关系类别,分类器和语义解析器也可以换成更准的分类模型和命名实体识别模型。

@buling13
Copy link
Author

buling13 commented Jun 24, 2024 via email

@XuekaiChen
Copy link
Owner

你说的是在neo4j页面只能看到25个节点吧。你点击关系类别的时候他默认的查询语句是“match p=()->() return p limit 25”,你把后面的limit去掉,在命令行自己输入一下就能全看到了。
image

@buling13
Copy link
Author

buling13 commented Jun 25, 2024 via email

@XuekaiChen
Copy link
Owner

可以的,只要语句正确,用graph对象.run()函数执行cypher语句。
个人认为cypher语句不用刻意学习,要干什么输入给ChatGPT,看几次怎么写就会了

@buling13
Copy link
Author

buling13 commented Jun 25, 2024 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

2 participants