Git Product home page Git Product logo

Comments (9)

hgliyuhao avatar hgliyuhao commented on September 1, 2024

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.

sdx9078 avatar sdx9078 commented on September 1, 2024

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.

hgliyuhao avatar hgliyuhao commented on September 1, 2024

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.

hgliyuhao avatar hgliyuhao commented on September 1, 2024

我又看了一下代码 149行
LC_score = (1 - np.abs(np.prod(scores, axis=2))).sum()

from activelearing4ner.

sdx9078 avatar sdx9078 commented on September 1, 2024

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.

hgliyuhao avatar hgliyuhao commented on September 1, 2024

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.

sdx9078 avatar sdx9078 commented on September 1, 2024

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.

hgliyuhao avatar hgliyuhao commented on September 1, 2024

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.

sdx9078 avatar sdx9078 commented on September 1, 2024

好的,非常感谢您的指点!

from activelearing4ner.

Related Issues (6)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.