Natural language processing
Natural language processing is the field of computing concerned with computationally analyzing, interpreting, transforming, or generating human language.
Natural Language Processing in Action, Second Edition
Natural language processing is the field of computing concerned with enabling machines to analyze, understand, generate, and interact using natural language.
- How it is used
- Enables search, writing assistance, and conversation by processing or generating natural-language text.
- How deep it goes
- Explains ambiguity and numerical representations, while keeping speech recognition and synthesis outside the text-processing focus.
- Examples
- Compares bag-of-words and transformer sarcasm detection on Twitter, and uses a TypeScript prompt to illustrate code generation.
- What you can do after
- Build it from scratch: create a simple chatbot or train a PyTorch convolutional neural network for text classification.
Introduction to Generative AI, Second Edition
Natural language processing is the field of computing concerned with analyzing, interpreting, generating, and transforming human language.
- How it is used
- Frames language technology from machine translation and chatbots through contemporary large language model applications.
- How deep it goes
- Explains major historical shifts, attention, training approaches, applications, and risks without descending into implementation details.
- Examples
- Uses machine translation, the Turing test, ELIZA, ChatGPT, summarization, question answering, coding, and conversational agents.
- What you can do after
- Evaluate language applications and use large language models while recognizing hallucinations, bias, imitation, and environmental costs.
Read how Introduction to Generative AI, Second Edition explains natural language processing →
Coding with AI
Natural language processing is the computational analysis and generation of human language, including interpreting text and producing meaningful language-related outputs.
- How it is used
- Supports language-aware applications and helps developers understand how generative AI tools process text.
- How deep it goes
- Defines tokenization and several text patterns, but deliberately remains a high-level overview rather than a deep treatment.
- Examples
- Uses virtual assistants, chatbots, document word counting, tokenized text, and classification tasks such as spam detection.
- What you can do after
- Build a simple document analyzer that tokenizes text and counts word occurrences.
Read how Coding with AI explains natural language processing →
Microsoft Azure in Action
Natural language processing is a branch of artificial intelligence that enables computers to understand, interpret, and generate human language.
- How it is used
- Uses NLP to support text-based customer interactions, book recommendations, summaries, and feedback analysis.
- How deep it goes
- Defines NLP and outlines model-selection and input-length trade-offs, without explaining NLP algorithms.
- Examples
- Uses a customer review requesting three similar books and Azure CLI examples for model deployment and prompting.
- What you can do after
- Apply it via Azure OpenAI Service to prototype recommendations while testing model speed, cost, and quality.
Read how Microsoft Azure in Action explains natural language processing →
Deep Learning with R, Third Edition
Natural language processing is the computational analysis and generation of human language.
- How it is used
- Frames computational language interpretation and manipulation through text preprocessing and classification.
- How deep it goes
- Progresses from definition and history to numeric preprocessing and simple classifiers, while deferring more complicated models such as Transformers.
- Examples
- Uses an early Russian-English translation system, chatbots, programming assistants, transcription, and machine translation as examples.
- What you can do after
- Build it from scratch by preprocessing text into numeric input and constructing simple text classifiers.
Read how Deep Learning with R, Third Edition explains natural language processing →
AI-Powered Search
Natural language processing is the computational analysis and generation of human language.
- How it is used
- Improves information retrieval by converting unstructured text into actionable data and interpreting queries and documents.
- How deep it goes
- Defines NLP, distinguishes query handling from document-level techniques, and reaches embeddings without detailing model internals.
- Examples
- Uses bilingual greetings, domain phrase lookup, and prior-session term co-occurrence as concrete examples.
- What you can do after
- Apply search-centric context and embeddings to improve query understanding, semantic retrieval, and result ranking.
Read how AI-Powered Search explains natural language processing →
Deep Learning with Python, Third Edition
The field of using computers to interpret, analyze, or generate human language, especially written text.
- How it is used
- Frames language processing through text preprocessing, classification, and progression toward more complicated models.
- How deep it goes
- Defines the field, surveys early rule-based translation, and stops short of detailed classifier or Transformer internals.
- Examples
- Uses numeric text preprocessing, simple classifiers, and an early Russian-to-English system evaluated on 60 handpicked sentences.
- What you can do after
- Build a simple text classifier after converting text input into numeric representations.
Read how Deep Learning with Python, Third Edition explains natural language processing →
Investing for Programmers
A field of computing concerned with analyzing and generating human language in textual or spoken form.
- How it is used
- Deploys language analysis to generate financial sentiment signals and distinguishes NLP from stock-price forecasting.
- How deep it goes
- Explains collection, parsing, scoring, and signal combination, but defers transformer and attention internals.
- Examples
- Uses collected media, recurring source moods, sentiment scores, scorecards, and historical trading datasets.
- What you can do after
- Apply it via web crawlers or APIs to create comparable sentiment signals for scorecards and backtests.
Read how Investing for Programmers explains natural language processing →
Grokking Machine Learning
Natural language processing is the computational analysis, transformation, or generation of human language.
- How it is used
- Applies neural networks to understanding spoken or written language and producing useful responses or transformations.
- How deep it goes
- Defines the field, surveys applications, and gives an intuition for recurrent memory without detailing training or implementation.
- Examples
- Uses sentiment classification, translation, speech-to-text, text summarization, and topic-specific customer-support chatbots.
- What you can do after
- Evaluate neural-network language applications and recognize when recurrent, LSTM, or GRU architectures are relevant.
Read how Grokking Machine Learning explains natural language processing →
Data-Driven Cybersecurity
Natural language processing is the computational analysis and generation of human language.
- How it is used
- Automates threat-intelligence review so security teams can identify emerging threats faster than manual reading.
- How deep it goes
- Explains keyword extraction, risk classification, and evaluation metrics, then demonstrates TF-IDF and logistic regression without detailing NLP internals.
- Examples
- Uses cybersecurity news articles, threat reports, keywords, high- and low-risk labels, classification reports, and confusion matrices.
- What you can do after
- Apply it via TF-IDF and logistic regression to classify cybersecurity articles and interpret precision, recall, F1-score, and accuracy.
Read how Data-Driven Cybersecurity explains natural language processing →
How Large Language Models Work
Natural language processing is the field concerned with technology for computers to understand, manipulate, and create human language.
- How it is used
- Explains the field underlying systems that understand, manipulate, and create human language.
- How deep it goes
- Defines NLP and situates LLMs within it, but defers detailed transformer mechanics.
- Examples
- Uses automated translation, ChatGPT, Copilot, Claude, Gemini, text generation, and a generated haiku.
- What you can do after
- Evaluate/understand how NLP relates to generative AI, LLMs, and text-based chatbot products.
Read how How Large Language Models Work explains natural language processing →
Knowledge Graphs and LLMs in Action
Natural language processing is the computational analysis, understanding, and generation of human language, including conventional pipelines composed of specialized models.
- How it is used
- Supports extracting domain-specific entities and relations from unstructured text for knowledge graph construction.
- How deep it goes
- Explains chained extraction models and deployment trade-offs, but stops short of implementation code or model internals.
- Examples
- Uses people, organizations, locations, and diseases as named-entity categories in raw text.
- What you can do after
- Evaluate traditional NLP and LLM workflows for producing domain-specific knowledge graphs.
Read how Knowledge Graphs and LLMs in Action explains natural language processing →
Starting Data Analytics with Generative AI and Python
Natural language processing is the field concerned with computational analysis and generation of human language.
- How it is used
- Deploys language analysis within text-mining workflows to organize unstructured content and support business insight.
- How deep it goes
- Descends from language structuring tasks to sentiment analysis, summarization, and topic modeling, while deferring detailed model internals.
- Examples
- Uses reviews, social-media posts, service interactions, phrases, sentences, parts of speech, entities, and relationships as working examples.
- What you can do after
- Apply it via generative AI or dedicated NLP libraries to structure text, analyze sentiment, summarize content, and extract customer insights.
LLMs in Production
Natural language processing is the field concerned with computationally processing and understanding human language.
- How it is used
- Frames language technology for understanding linguistic meaning, modeling history, and production deployment.
- How deep it goes
- Explains linguistic foundations, modeling milestones, and representation challenges, but stops short of detailed algorithms or implementation procedures.
- Examples
- Uses N-grams, naive Bayes, neural networks, embeddings, temperature scales, image pixels, and sound measurements as comparison points.
- What you can do after
- Evaluate NLP systems with greater awareness of representation limits, modeling alternatives, and text-specific production risks.
Read how LLMs in Production explains natural language processing →
Build AI-Enhanced Web Apps
Natural language processing is the computational processing and understanding of human language in text or speech.
- How it is used
- Integrates pretrained language models into conversational web applications without requiring a custom model.
- How deep it goes
- Explains transformer context and self-attention, then stops short of model training or mathematical treatment.
- Examples
- Uses Astra AI, follow-up questions, conversational history, pronoun resolution, and the “green eggs and …” completion.
- What you can do after
- Build conversational language features with React, Node.js, Vite, and OpenAI REST APIs.
Read how Build AI-Enhanced Web Apps explains natural language processing →
Related concepts
- machine learningkind of · Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
- tokenizationhas part · Tokenization is the process of dividing text or other sequential input into discrete units called tokens for computational processing.
- artificial intelligencekind of · Artificial intelligence is the field concerned with creating computational systems that perform tasks associated with human intelligence, such as learning, reasoning, perception, or decision-making.
- conversational aiused by · Conversational AI is artificial intelligence that enables software systems to interact with users through natural-language dialogue.
- sentiment analysisincludes · Sentiment analysis is the computational identification, classification, or measurement of opinions, attitudes, emotions, or evaluative polarity expressed in text or other data.
- retrieval-augmented generationincludes · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.