I checked and re-labeled FinRE dataset with these rules

[A-baoYang]

I re-labeled the FinRE dataset as FinRE-v2 with these rules below:

1. Extend 订单 to 订单, 被下订单 relations so that can capture the characters between "provider" and "client"
2. Add relation 砍单, 被砍单: if 增持 and 减持 exist, there should have 订单 and 砍单
3. Check and extend company relations in [交易, 签约, 重组]: more specific capture what kind of trading, eg. 买资, 收购, 持股, 增持 or 减持, etc.

The entire relation classes schema:

unknown 0
注资 1
拥有 2
纠纷 3
自己 4
增持 5
重组 6
买资 7
签约 8
持股 9
交易 10
入股 11
转让 12
成立 13
分析 14
合作 15
帮助 16
发行 17
商讨 18
合并 19
竞争 20
订单 21
砍单 22
减持 23
合资 24
收购 25
借壳 26
欠款 27
被发行 28
被转让 29
被成立 30
被注资 31
被持股 32
被拥有 33
被收购 34
被帮助 35
被借壳 36
被买资 37
被欠款 38
被增持 39
拟收购 40
被减持 41
被分析 42
被入股 43
被拟收购 44
被重组 45
被下订单 46
被砍单 47

The re-labeled dataset is provided through Google Drive link on my Github repo: https://github.com/A-baoYang/NLP-techniques-chinese/tree/main/NLU/Classification/RelationClassification

[ningding97]

Thanks for your contribution，it seems reasonable!