Natural Language Processing and Large Language Models: Theory, Hand-on Codes, and Case Studies (en Inglés) - Chengqing Zong

The open access book unlocks the full potential of Natural Language Processing (NLP) through a comprehensive and hands-on guide that bridges foundational theory and cutting-edge practice. Whether you're a student, researcher, or industry practitioner, it enables you to build and deploy state-of-the-art NLP models—from classical statistical approaches to modern neural architectures and large language models (LLMs)—with confidence and clarity.

Unlike traditional texts that focus solely on concepts, this book offers a practical journey through real-world NLP applications, including sentiment analysis, information extraction, summarization, text matching, question answering, and machine translation. Each chapter is grounded in executable code and datasets, presented in the form of Jupyter Notebooks hosted on Baidu AI Studio. Readers can access free cloud-based resources to run, test, and modify models, making the learning experience interactive and scalable.

Designed for senior undergraduate and graduate students in computer science and AI-related fields, as well as NLP beginners and developers, the book demystifies key concepts such as Transformer, BERT, GPT, ERNIE, and RLHF through step-by-step case studies. It also addresses practical challenges—such as data preprocessing, model fine-tuning, and deployment—that reflect real-world R&D scenarios. Readers don’t just learn what works in NLP—they understand how and why it works.

With its task-driven structure, fully tested codebase, and ready-to-use implementations, this book serves as a valuable academic and technical resource for anyone seeking to master applied NLP with modern deep learning techniques.