训练关键信息抽取模型(KIE)时,RE的关系怎么标注? #12721
Replies: 4 comments
-
同问 +1 |
Beta Was this translation helpful? Give feedback.
0 replies
-
自己修改成other,并且将 key_cls 改成 label |
Beta Was this translation helpful? Give feedback.
0 replies
-
楼主搞明白了吗 我也想问 |
Beta Was this translation helpful? Give feedback.
0 replies
-
因PPOCRLabel已经搬家了,后续有问题请移步PPOCRLabel提问哈! |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
根据官方文档(https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/ppstructure/kie/how_to_do_kie.md#22-%E8%AE%AD%E7%BB%83KIE%E6%A8%A1%E5%9E%8B)

我只找到SER的标注方式,使用命令:PPOCRLabel --lang ch --kie=True打开PPOCRLabel后,页面多了关键字列表:
也并没有文档中所说的other而是None,导出标签的字段为"key_cls": "None"。

准备进行下一步RE标注时发现不知从何入手,导出标签也没有label字段。官方文档实例图如下:
想求教各位大佬与官方,怎么进行RE标注,实现关键词之间的关系?以及求教具体训练的方法。万分感谢!
Beta Was this translation helpful? Give feedback.
All reactions