Comments (9)
Maximum Normalized Log-Probality(MNLP),基于 LC 并且考虑到生成中的序列长度对于不确定性的影响,我们做一个 normalization(即除以每个句子的长度)
在实验的过程中发现,句子长度越大,不确定度越大,为了让MNLP只对实体敏感,降低句子长度造成的影响,每个分数都除以每个句子的长度 512可以看成一个常数
from activelearing4ner.
但是我看MNLP的定义里,是要进行一个log运算的哎,直接除以每个句子的长度是不是和MNLP定义有点区别。。。
from activelearing4ner.
是的 论文里是每一个点概率输出的 log 值求和来,我理解log是一个单调递增,所以这个数值不管怎么变换都应该表征句子不确定度的大小,我记得当初实验的时候求log求和以后每个值都很小看起来不太直观,就按照我的观感进行了修改
from activelearing4ner.
我又看了一下代码 149行
LC_score = (1 - np.abs(np.prod(scores, axis=2))).sum()
from activelearing4ner.
也就是说,现在的LC_score也用了log运算吗,但是论文原文中LC的式子里好像没涉及到log运算哎?而且如果是log运算的话不是要用到np.log吗?
from activelearing4ner.
ooo my bad ! 没有用到。
这个还是我自己按照理解实现的版本
from activelearing4ner.
hh感谢您的回复。请问您有与这个代码相关的论文吗?我看您提出的entry_MNLP_confidence**很合理,如果有相关论文的话我想去拜读一下
from activelearing4ner.
这个是实践时候发现的 后面就没太关注这方面了
Subsequence Based Deep Active Learning for Named Entity Recognition 2021 你可以看看这个 也是在原论文基础上的改进 感觉这个方法还有蛮大的改进空间
from activelearing4ner.
好的,非常感谢您的指点!
from activelearing4ner.
Related Issues (6)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from activelearing4ner.