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

你好,得到result.json 文件后,这个文件该如何理解? #11

Closed
eve1104 opened this issue Aug 23, 2021 · 4 comments
Closed

Comments

@eve1104
Copy link

eve1104 commented Aug 23, 2021

{"title": "Miguel Riofr\u00edo", "h_idx": 0, "t_idx": 1, "r": "P569", "evidence": []} 我得到title: "Miguel Riofr\u00edo 有多个,他们是哪一句在哪里体现?得到的文件究竟该如何理解?

@BenfengXu
Copy link
Owner

BenfengXu commented Aug 23, 2021

每一条数据应该包含 title / vertexSet / sents 等字段,可以按照title去检索到对应的数据,这个应该是唯一的
"h_idx"代表subject实体在 vertexSet字段中的 index,即vertexSet[h_idx]
同理t_idx,据此可索引到对应的实体,以及找到它们在段落、句子中的位置
"r"代表对应的关系

@eve1104
Copy link
Author

eve1104 commented Aug 25, 2021

Thank you for answering my question.

@YuanEric88
Copy link

请问result.json这个数据结构的设计出于什么考虑的呢?当前的结果中每一个element是一个实体词对的分类结果,为什么不以title为单位进行存储,也就是一个element包含了一个title中所有的实体词对分类信息?现在的存储方式看起来相对杂乱

@BenfengXu
Copy link
Owner

BenfengXu commented Aug 30, 2021

请问result.json这个数据结构的设计出于什么考虑的呢?当前的结果中每一个element是一个实体词对的分类结果,为什么不以title为单位进行存储,也就是一个element包含了一个title中所有的实体词对分类信息?现在的存储方式看起来相对杂乱

和官方Baseline的实现以及Codalab榜单的提交要求一致的哈,请参考:
https://github.com/thunlp/DocRED
https://competitions.codalab.org/competitions/20717#results

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