Getting Started with Natural Language Processing

Natural language processing connects the text people write with the applications that search, classify, and interpret it. In Getting Started with Natural Language Processing, Ekaterina Kochmar builds that connection step by step, introducing core ideas through practical Python examples and applications.

The book moves from introductory NLP concepts into information search and extraction, author profiling, sentiment analysis, topic analysis, and named-entity recognition. Along the way, readers see how individual techniques fit into larger language-processing tasks.

Learn NLP through practical applications

Rather than treating natural language processing as a collection of disconnected terms, the book places techniques in context. Readers encounter tokenization and text normalization, then move on to methods such as stemming, part-of-speech tagging, parsing, and linguistic feature engineering as they relate to the problems being explored.

From search to sentiment and topics

The chapter sequence covers several familiar applications: finding information in text, extracting information, profiling authors, analyzing sentiment, and identifying topics. Later chapters introduce topic modeling and named-entity recognition, rounding out an introduction that spans both foundational methods and practical uses.

Python tools in the workflow

Examples draw on libraries including NLTK, spaCy, and scikit-learn, with additional tools such as gensim and pandas appearing in relevant chapters. Seeing these tools used across different tasks can help readers understand how NLP methods are put to work in code.

A starting point for aspiring NLP practitioners

The publisher describes basic Python skills as the prerequisite; previous experience with NLP is not required. Readers who want an approachable, application-led introduction to language processing can use the book to build familiarity with its central concepts and the kinds of tasks they support.