Overview
Who this competition fits
适合已能用 PaddlePaddle 2.0+ 训练端到端深度学习模型、想练习中文短文本多分类的个人开发者。任务直接使用新闻标题和标签训练,了解中文文本预处理与分类模型即可进入。
Read the original official blurb
基于THUCNews数据集的文本分类任务。 THUCNews是根据新浪新闻RSS订阅频道2005~2011年间的历史数据筛选过滤生成,包含74万篇新闻文档,参赛者需要根据新闻标题的内容用算法来判断该新闻属于哪一类别。 Official tags: 文本分类. Sign-ups: 907.
Resources
What this competition gives you
There is a baseline you can run as-is — starting from it is usually far faster than building from scratch.
Preparation
From registration to a first submission
- 01
PaddlePaddle 2.0+
- 02
中文文本分类
- 03
新闻标题预处理
- 04
多分类模型训练
- 05
ZIP结果文件生成
- 06
AI Studio Notebook
Before you commit: 关键不仅是训练出能区分14类新闻标题的模型,还要严格按测试集原顺序输出预测:result.txt 每行一个类别,且总行数必须为83599;行数或顺序不符即成绩无效。提交的预测结果和原始代码还必须基于飞桨框架生成。
Source
How this page was assembled
Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.
- Official competition page
- Baidu AI Studio
- Last checked
- Not recorded