Code Monkey home page Code Monkey logo

multi-label_text_classification's Introduction

Multi-label_text_classification

开课吧&后厂理工学院 百度NLP项目2:百度试题数据集多标签文本分类

数据说明

原始数据集为高中地理,历史,生物,政治四门学科数据,每个学科下各包含第一层知识点,如历史下分为近代史,现代史,古代史
原始数据示例:

[题目]
我国经济体制改革首先在农村展开。率先实行包产到组、包产到户的农业生产责任制的省份是( )
①四川 ②广东 ③安徽 ④湖北A. ①③B. ①④C. ②④D. ②③题型: 单选题|难度: 简单|使用次数: 0|纠错复制收藏到空间加入选题篮查看答案解析答案:A解析:本题主要考察的是对知识的识记能力,比较容易。根据所学知识可知,在四川和安徽,率先实行包产到组、包产到户的农业生产责任制,故①③正确;②④不是。所以答案选A。知识点:
[知识点:]
经济体制改革,**的振兴

对数据处理:

  • 将数据的[知识点:]作为数据的第四层标签,显然不同数据的第四层标签数量不一致
  • 仅保留题目作为数据特征,删除[题型]及[答案解析]

4层标签数据集

模型

  1. fasttest
  2. textcnn
  3. gcn
    GCN with Multi Labels
    GCN_AAAI2019

ps: 4x2080Ti 显存不足以支持tf.sparse_tensor_dense_matmul(x, y)[layer.py line 33] 使用CPU训练即可

  1. bert
  2. xlnet(doing)

实验结果

数据集 模型 类别 Acc Micro-F1 Macro-F1 备注
Baidu FastText 95 - 0.421 0.234 epoch 1000, ngram 5, dim 50
Baidu TextCnn 95 - 0.00478 0.028 epoch 10, lr 0.005, padding 128
Baidu GCN 95 - 0.8755 0.6914 gcn
Baidu BERT 21 0.7958 0.941 0.163 BERT 3 layers labels result
Baidu BERT 95 0.5788 0.917 0.781 only BERT

学员成果展示

学员优秀作业一:

学员:张*宁同学
推荐理由:项目代码完整,笔记清晰有调理
地址:https://github.com/Light2077/Text-Classification

学员优秀作业二:

学员:邓*勇同学
推荐理由:项目代码结构清晰,完整,使用tensorflow-serving+nvidia-docker+grpc部署roberta模型
地址:https://github.com/DengYangyong/exam_annotation 
这个学员有自己的公众号,写的非常棒,地址:https://mp.weixin.qq.com/s/PgC7lZxikKyGMlMNpnOLLA

multi-label_text_classification's People

Contributors

nocater avatar alanwgy avatar

Watchers

James Cloos avatar

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.