Git Product home page Git Product logo

Comments (7)

liqunhit avatar liqunhit commented on August 24, 2024

补充:人工定义的类目体系是否每个节点的层级都是一样的?比如有些只到二级,有些到三级。这样可以吗?

from hierarchical-multi-label-text-classification.

RandolphVI avatar RandolphVI commented on August 24, 2024

@liqunhit

很好的问题,现目前解决的主要还是人工定义的类目体系是规定统一的,即记录均包含四级,不存在一部分标记到四级,另一部分仅标记到二级。

对于你阐述的问题,有几个解决的方案:

  1. 对仅含有二级标签的数据进行标签扩充,例如给定这些数据三、四级的标签为“unkown”(全新的一个类别),在后续模型训练预测上代码运行不存在不影响,在进行指定各个层级的标签预测时候,先通过预测数据后处理之后再进行评价指标运算。
  2. 去除仅标记到二级标签、或者仅标记到三级标签的数据。
  3. 使用网络权重迁移实现。即先对仅标记到二级标签的数据进行模型训练,模型训练完毕之后的网络参数迁移传递到给仅标记到三级标签的数据进行模型训练,以此类推(这个方法自然工作量比较大)。当然也可以分离数据,对标记到不同层级的数据进行分别网络训练,指标评价的时候也通过训练好的不同网络预测即可。

from hierarchical-multi-label-text-classification.

liqunhit avatar liqunhit commented on August 24, 2024

明白了,非常感谢回复。
另外还有个问题请教下,咱们这里文本的表示为啥用的是bilstm,有实验过BERT吗?

from hierarchical-multi-label-text-classification.

RandolphVI avatar RandolphVI commented on August 24, 2024

@liqunhit

Bi-LSTM 我觉得已经够了,整体的模型的参数其实很大了,如果要考虑使用 BERT,成本太高。

from hierarchical-multi-label-text-classification.

liqunhit avatar liqunhit commented on August 24, 2024

使用BERT+FLAT分类(不做层次分类),有对比过效果吗?

from hierarchical-multi-label-text-classification.

RandolphVI avatar RandolphVI commented on August 24, 2024

@liqunhit

暂时没有尝试过

from hierarchical-multi-label-text-classification.

liqunhit avatar liqunhit commented on August 24, 2024

好的,非常感谢回复。

from hierarchical-multi-label-text-classification.

Related Issues (20)

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.