book

Natural Language Processing Fundamentals

Name: Natural Language Processing Fundamentals
ISBN: 9781789954043

by Sohom Ghosh, Dwight Gunning

March 2019

Beginner

374 pages

6h 36m

English

Packt Publishing

Read now

Unlock full access

Preface
About the BookAbout the AuthorsLearning ObjectivesAudienceApproachHardware RequirementsSoftware RequirementsConventionsInstallation and SetupWorking with the Jupyter Notebook Importing Python Libraries Installing the Code BundleAdditional Resources
1. Introduction to Natural Language Processing
IntroductionHistory of NLPText Analytics and NLPExercise 1: Basic Text AnalyticsVarious Steps in NLPTokenizationExercise 2: Tokenization of a Simple SentencePoS TaggingExercise 3: PoS TaggingStop Word RemovalExercise 4: Stop Word RemovalText NormalizationExercise 5: Text NormalizationSpelling CorrectionExercise 6: Spelling Correction of a Word and a SentenceStemmingExercise 7: StemmingLemmatizationExercise 8: Extracting the base word using LemmatizationNERExercise 9: Treating Named EntitiesWord Sense DisambiguationExercise 10: Word Sense DisambiguationSentence Boundary DetectionExercise 11: Sentence Boundary DetectionActivity 1: Preprocessing of Raw TextKick Starting an NLP ProjectData CollectionData PreprocessingFeature ExtractionModel DevelopmentModel AssessmentModel DeploymentSummary
2. Basic Feature Extraction Methods
IntroductionTypes of DataCategorizing Data Based on StructureCategorization of Data Based on ContentCleaning Text DataTokenizationExercise 12: Text Cleaning and TokenizationExercise 13: Extracting n-gramsExercise 14: Tokenizing Texts with Different Packages – Keras and TextBlobTypes of Tokenizers Exercise 15: Tokenizing Text Using Various TokenizersIssues with TokenizationStemmingRegexpStemmerExercise 16: Converting words in gerund form into base words using RegexpStemmerThe Porter StemmerExercise 17: The Porter StemmerLemmatizationExercise 18: LemmatizationExercise 19: Singularizing and Pluralizing WordsLanguage TranslationExercise 20: Language TranslationStop-Word RemovalExercise 21: Stop-Word RemovalFeature Extraction from TextsExtracting General Features from Raw TextExercise 22: Extracting General Features from Raw TextActivity 2: Extracting General Features from TextBag of WordsExercise 23: Creating a BoWZipf's Law Exercise 24: Zipf's LawTF-IDFExercise 25: TF-IDF RepresentationActivity 3: Extracting Specific Features from TextsFeature EngineeringExercise 26: Feature Engineering (Text Similarity)Word CloudsExercise 27: Word CloudsOther VisualizationsExercise 28: Other Visualizations (Dependency Parse Trees and Named Entities)Activity 4: Text VisualizationSummary
3. Developing a Text classifier
IntroductionMachine LearningUnsupervised LearningHierarchical ClusteringExercise 29: Hierarchical ClusteringK-Means ClusteringExercise 30: K-Means ClusteringSupervised LearningClassificationLogistic RegressionNaive Bayes ClassifiersK-Nearest NeighborsExercise 31: Text Classification (Logistic regression, Naive Bayes, and KNN)RegressionLinear RegressionExercise 32: Regression Analysis Using Textual DataTree MethodsRandom ForestGBM and XGBoostExercise 33: Tree-Based Methods (Decision Tree, Random Forest, GBM, and XGBoost)SamplingExercise 34: Sampling (Simple Random, Stratified, Multi-Stage)Developing a Text ClassifierFeature ExtractionFeature EngineeringRemoving Correlated FeaturesExercise 35: Removing Highly Correlated Features (Tokens)Dimensionality ReductionExercise 36: Dimensionality Reduction (PCA)Deciding on a Model TypeEvaluating the Performance of a ModelExercise 37: Calculate the RMSE and MAPEActivity 5: Developing End-to-End Text ClassifiersBuilding Pipelines for NLP ProjectsExercise 38: Building Pipelines for NLP ProjectsSaving and Loading ModelsExercise 39: Saving and Loading ModelsSummary
4. Collecting Text Data from the Web
IntroductionCollecting Data by Scraping Web PagesExercise 40: Extraction of Tag-Based Information from HTML FilesRequesting Content from Web PagesExercise 41: Collecting Online Text Data Exercise 42: Analyzing the Content of Jupyter Notebooks (in HTML Format)Activity 6: Extracting Information from an Online HTML PageActivity 7: Extracting and Analyzing Data Using Regular ExpressionsDealing with Semi-Structured DataJSONExercise 43: Dealing with JSON FilesActivity 8: Dealing with Online JSON FilesXMLExercise 44: Dealing with a Local XML FileUsing APIs to Retrieve Real-Time DataExercise 45: Collecting Data Using APIsAPI CreationActivity 9: Extracting Data from TwitterExtracting Data from Local FilesExercise 46: Extracting Data from Local FilesExercise 47: Performing Various Operations on Local FilesSummary
5. Topic Modeling
IntroductionTopic DiscoveryDiscovering ThemesExploratory Data AnalysisDocument ClusteringDimensionality ReductionHistorical AnalysisBag of Words Topic Modeling AlgorithmsLatent Semantic AnalysisLSA – How It WorksExercise 48: Analyzing Reuters News Articles with Latent Semantic AnalysisLatent Dirichlet AllocationLDA – How It WorksExercise 49: Topics in Airline TweetsTopic FingerprintingExercise 50: Visualizing Documents Using Topic VectorsActivity 10: Topic Modelling Jeopardy QuestionsSummary
6. Text Summarization and Text Generation
IntroductionWhat is Automated Text Summarization?Benefits of Automated Text SummarizationHigh-Level View of Text SummarizationPurposeInputOutputExtractive Text SummarizationAbstractive Text SummarizationSequence to Sequence Encoder DecoderTextRankExercise 51: TextRank from ScratchSummarizing Text Using GensimActivity 11: Summarizing a Downloaded Page Using the Gensim Text SummarizerSummarizing Text Using Word FrequencyExercise 52: Word Frequency Text SummarizationGenerating Text with Markov ChainsMarkov ChainsExercise 53: Generating Text Using Markov ChainsSummary
7. Vector Representation
IntroductionVector DefinitionWhy Vector Representations?EncodingCharacter-Level EncodingExercise 54: Character Encoding Using ASCII ValuesExercise 55: Character Encoding with the Help of NumPy ArraysPositional Character-Level EncodingExercise 56: Character-Level Encoding Using PositionsOne-Hot EncodingKey Steps in One-Hot EncodingExercise 57: Character One-Hot Encoding – ManualExercise 58: Character-Level One-Hot Encoding with KerasWord-Level One-Hot EncodingExercise 59: Word-Level One-Hot EncodingWord EmbeddingsWord2VecExercise 60: Training Word VectorsUsing Pre-Trained Word VectorsExercise 61: Loading Pre-Trained Word VectorsDocument VectorsUses of Document VectorsExercise 62: From Movie Dialogue to Document VectorsActivity 12: Finding Similar Movie Lines Using Document VectorsSummary
8. Sentiment Analysis
IntroductionWhy is Sentiment Analysis Required?Growth of Sentiment AnalysisMonetization of EmotionTypes of SentimentsKey Ideas and TermsApplications of Sentiment AnalysisTools Used for Sentiment AnalysisNLP Services from Major Cloud ProvidersOnline MarketplacesPython NLP LibrariesDeep Learning LibrariesTextBlobExercise 63: Basic Sentiment Analysis Using the TextBlob LibraryActivity 13: Tweet Sentiment Analysis Using the TextBlob libraryUnderstanding Data for Sentiment AnalysisExercise 64: Loading Data for Sentiment AnalysisTraining Sentiment ModelsExercise 65: Training a Sentiment Model Using TFIDF and Logistic RegressionSummary
Appendix
1. Introduction to Natural Language ProcessingActivity 1: Preprocessing of Raw Text2. Basic Feature Extraction MethodsActivity 2: Extracting General Features from TextActivity 3: Extracting Specific Features from TextsActivity 4: Text Visualization3. Developing a Text classifierActivity 5: Developing End-to-End Text Classifiers4. Collecting Text Data from the WebActivity 6: Extracting Information from an Online HTML PageActivity 7: Extracting and Analyzing Data Using Regular ExpressionsActivity 8: Dealing with Online JSON FilesActivity 9: Extracting Data from Twitter5. Topic ModelingActivity 10: Topic Modelling Jeopardy Questions6. Text Summarization and Text GenerationActivity 11: Summarizing a Downloaded Page Using the Gensim Text Summarizer7. Vector RepresentationActivity 12: Finding Similar Movie Lines Using Document VectorsSolution8. Sentiment AnalysisActivity 13: Tweet Sentiment Analysis Using the TextBlob library

Content preview from Natural Language Processing Fundamentals

7. Vector Representation

Learning Objectives

By the end of this chapter, you will be able to:

Describe the need for vector representation in Natural Language Processing (NLP)
Identify the various ways that text can be represented as vectors
Describe word vectors and their various forms
Implement vector arithmetic
Describe document vectors

In this chapter, you will be learning about various encoding techniques using which a text can be represented as vector.

Introduction

The previous chapters laid a firm foundation for NLP. But now we will go deeper into a key topic – one that gives us surprising insights into how a language works and how some of the key advances in human computer interaction are facilitated. At the heart of NLP is ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Getting Started with Natural Language Processing

Publisher Resources

ISBN: 9781789954043

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design