JUSTSUJAY/nlp-zero-to-hero：NLP Zero 到 Hero 仅用 10 个核

项目介绍

JUSTSUJAY/nlp-zero-to-hero 是一个托管在 GitHub 上的开源项目，主要使用 Jupyter Notebook 编写，采用 MIT License 许可证，目前获得 598 个 Star、92 次 Fork。

仓库全名: JUSTSUJAY/nlp-zero-to-hero

README 摘要

Natural Language Processing: Zero to Hero! Welcome to Theory and Hands-on experience of NLP. In this repository, I've covered almost everything that you need to get started in the world of NLP, starting from Tokenizers to the Transformer Architecuture. By the time you finish this, you will have a solid grasp over the core concepts of NLP. The motive of this repository is to give you the core intuition and by the end…

完整内容见 GitHub 原始 README 或本页。

常见问题

nlp-zero-to-hero 用什么语言开发？

主要使用 Jupyter Notebook 编写，采用 MIT License 许可证，目前有 598 个 Star。

nlp-zero-to-hero 可以免费商用吗？

如何获取 nlp-zero-to-hero 的源码？

可以直接克隆仓库：git clone https://github.com/JUSTSUJAY/nlp-zero-to-hero.git，默认分支为 main；安装与运行步骤见仓库 README。

nlp-zero-to-hero 最近还在维护吗？

仓库最近一次更新为 2024年9月23日，当前没有未关闭的 Issue；Star 数为 598，可作为社区活跃度的参考。

关于

GitHub 原始描述（英文）

NLP Zero to Hero in just 10 Kernels

ai andrej-karpathy data-science machine-learning nlp zero-to-hero

MIT License
598 Stars
92 Forks
6 Watching

描述取自 GitHub 官方 API，保持仓库作者书写的原文。

简要分析

热度分

788

价值分

387

活跃状态

活跃

GitHub

语言占比

Jupyter Notebook

贡献者

JUSTSUJAY

Natural Language Processing: Zero to Hero!

Welcome to Theory and Hands-on experience of NLP.

In this repository, I’ve covered almost everything that you need to get started in the world of NLP, starting from Tokenizers to the Transformer Architecuture. By the time you finish this, you will have a solid grasp over the core concepts of NLP.

The motive of this repository is to give you the core intuition and by the end of this you’ll know how things evolved over the years and why they are the way they are.

alt text

Image Generated by Ideogram

1. Tokenization

2. Preprocessing

3. Bag of Words and Similarity

4. TF-IDF and Document Search

5. Naive Bayes Text Classification

6. LDA Topic Modelling

7. Word Embeddings

8. Recurrent Neural Networks (RNNs) and Language Modelling

9. Machine Translation and Attention

10. Transformers

How do I use this repository?

Considering the computational power required for ML and DL, it is advised to use Google Colab or Kaggle Kernels.
You can click on to open the notebook in Colab.
You can click on to open the notebook in Kaggle.
For some of the notebooks, Kaggle datasets are used, and some of them are in Gigabytes.
For quicker loading of those datasets, it is advised to open them in Kaggle using corresponding tags.
Opening the Kaggle Kernel does not directly attach the dataset required for the notebook.
You are required to attach the dataset whose link has been provided in the respective notebooks, which you will find as you progress through them.
Start with the Tokenization Notebook and move forward sequentially.
Take your time to understand the concepts and code. It is specifically designed to be easy to understand and to be done at your own pace.
Make sure you have a basic understanding of Python programming before starting.
If you encounter any issues or have questions, feel free to open an issue in the GitHub repository.
Don’t forget to star the repository if you find it helpful!

Contributing

You are more than welcome to contribute to this repository. You can start by opening an issue or submitting a pull request. If you have any questions, feel free to reach out to me on X

If you have any resources that you think would be helpful for others, feel free to open an issue or submit a pull request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Star History

暂无评论

nlp-zero-to-hero