gaohongkui / tplinker-ner Goto Github PK
View Code? Open in Web Editor NEWTPlinker for NER 中文/英文命名实体识别
License: Apache License 2.0
TPlinker for NER 中文/英文命名实体识别
License: Apache License 2.0
请问对一个已有标注的ner数据集,若采用扩充后的标签库,其对应的handshaking矩阵具体是什么形式呢?
扩充后标签库的部分标签与实体关系有关,但是ner数据集上没有主语或宾语等标注。那涉及到标签库该类标签时,handshaking矩阵对应坐标的值是多少呢?
例如有个输入文本“小明去北京”。包含两个实体类型“人名”和“地名”,其对应标签库有10个标签。其中标签“人名-SH to OH”的含义是“人名关系下主语的头到宾语的头”,ner标注中并没有包含这样的信息,那handshaking矩阵对应坐标的值应该为0吗?
如果handshaking矩阵对应坐标确实为0的话,那矩阵是不是有点太稀疏了?
如果可以解答一二,感激不尽。
你好!请问换成自己的数据集之后训练结果全是0可能会是什么原因,我的数据集格式是完全符合要求的,不过标签不一样,需要修改代码吗?在哪里改标签的代码?谢谢解答!
您引用的苏神文章里写的是多标签分类问题,我不太理解实体抽取算法为什么算作是多标签分类问题?
抱歉我是初学者。按照我的理解在矩阵中给两个位置加一个标签,最后得到的也是单个的一种类型而不是多个不是吗?
打扰了!你的作品对我帮助很大,希望可以多多学习!
Thanks for your work. The repo for CLUENER2020 presents the F1 score on each entity class and the macro F1 score over them, while it seems that your 0.9111 is the micro F1 score, Could you please provide the macro F1 score (and the F1 score on each entity class) so that we can see the improvement more clearly?
你好,我把项目下载重新run,发现结果全为0 ,这是怎么回事啊?用得是你的数据集。
请问换成英文数据集的话,token_span和char_span是以字符为单位呢,还是以单词为单位呢
如:Tom:字符为单位,索引是[0,2];单词为单位是[0,0]
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.