Practical Natural Language Processing

A Comprehensive Guide to Building Real-World NLP Systems

Sowmya Vajjala, Bodhisattwa P. Majumder, Anuj Gupta, Harshit Surana

Endorsed by: Zachary Lipton, Sebastian Ruder, Marc Najork, Monojit Choudhury, Vinayak Hegde, Mengting Wan, Siddharth Sharma, & Ed Harris Foreword by: Julian McAuley

Homepage: www.practicalnlp.ai Published by O'Reilly Media, 2020

---

Book Structure

Please note that the code repository is still under development and review.

All the notebooks will be crystalized in the coming months. 

The notebooks have been tested on an ubuntu machine running python 3.6. 

Currently, we are using TF1.x. We will migrate to TF2.x in the coming months.  

---

✨ A newer version compatible with Ubuntu 23 is being added in pnlp-refactor-ubuntu23.

We thank everyone, especially the educators & universities, for their feedback in pointing out the issues & improving the accessibility of the notebooks.

---

🚩 Details of the repository roadmap could be found here

---

Open the repository in Google Colab:

Open the repository in Jupyter nbviewer:

Chapterwise folders:

• Chapter 1: NLP: A Primer (only figures & outline)

• Chapter 2: NLP Pipeline

• Chapter 3: Text Representation

• Chapter 4: Text Classification

• Chapter 5: Information Extraction

• Chapter 6: ChatBots

• Chapter 7: Topics in Brief

• Chapter 8: Social Media

• Chapter 9: E-commerce and Retail

• Chapter 10: Healthcare, Finance and Law

• Chapter 11: End-to-End NLP Process

Contributors to Codebase:

• Varun Purushotham
• Kartikay Bagla
• Jitin Kapila
• Vishal Gupta
• Taranjeet Singh
• Shreyans Dhankhar
• Kumarjit Pathak
• Ernest Kirubakaran Selvaraj
• Ayush Datta
• Rui Shu
• Nachiketh Suresh
• Jatin Papreja
• Kumar Apurva
• Sukeerat Goindi
• Abhijeetsingh Meena

Found a Bug?

If the bug is in book text, please enter a errata here: https://www.oreilly.com/catalog/errata.csp?isbn=0636920262329

If the bug is in the codebase: Great! Please read this how can you help us improve the codebase