[go: nahoru, domu]

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

[Question]: 请教关于uie的细粒度实体识别和多任务联合抽取 #5400

Open
YYGe01 opened this issue Mar 24, 2023 · 0 comments
Open
Assignees
Labels
question Further information is requested triage

Comments

@YYGe01
Copy link
YYGe01 commented Mar 24, 2023

请提出你的问题

感谢开源。
我要同时做三个任务:细粒度实体识别、关系抽取、文本分类任务。

text1:姚明捐赠了厦门大学
text1:姚明捐赠了儿童基金会

需求:

实体识别:我需要抽取出实体(人名,学校,机构等),其中实体还需要细粒度抽取,如人名还要区分是(运动员、歌手、演员等),
关系抽取:抽取两个三元组(姚明,捐赠,厦门大学)(姚明,捐赠,儿童基金会),这里厦门大学是学校实体,儿童基金会是机构实体。
文本分类:比如是否是(娱乐新闻、体育新闻等)

我应该如何构建我的schema呢?
我目前方案如下:

[
    {"人名":["捐赠", "情感倾向['运动员','歌手']"]}, # 关系抽取,细粒度识别同时作为关系看待
    "机构",  # 实体识别,因为subject人名和不同的object有关系,所以无法通过捐赠关系判断,需要另外识别
    "学校",  # 实体识别,同上
    "情感倾向['娱乐','体育']",  # 文本分类
]

请问我这样设计schema是否合理呢。
另外,我这里如果同时进行三个任务,不知道可不可行,不同的任务同时共享编码层,会不会相互影响各自任务的性能呢,谢谢。

@YYGe01 YYGe01 added the question Further information is requested label Mar 24, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested triage
Projects
None yet
Development

No branches or pull requests

3 participants