Applied natural language processing with Python : implementing machine learning and deep learning algorithms for natural language processing /: implementing machine learning and deep learning algorithms for natural language processing. (2018)

• Record Type: Book
• Further Information: Note: Taweh Beysolow II.
• Authors: Beysolow, Taweh
• Contents: Intro; Table of Contents; About the Author; About the Technical Reviewer; Acknowledgments; Introduction; Chapter 1: What Is Natural Language Processing?; The History of Natural Language Processing; A Review of Machine Learning and Deep Learning; NLP, Machine Learning, and Deep Learning Packages with Python; TensorFlow; Keras; Theano; Applications of Deep Learning to NLP; Introduction to NLP Techniques and Document Classification; Topic Modeling; Word Embeddings; Language Modeling Tasks Involving RNNs; Summary; Chapter 2: Review of Deep Learning Multilayer Perceptrons and Recurrent Neural NetworksToy Example 1: Modeling Stock Returns with the MLP Model; Learning Rate; Vanishing Gradients and Why ReLU Helps to Prevent Them; Loss Functions and Backpropagation; Recurrent Neural Networks and Long Short-Term Memory; Toy Example 2: Modeling Stock Returns with the RNN Model; Toy Example 3: Modeling Stock Returns with the LSTM Model; Summary; Chapter 3: Working with Raw Text; Tokenization and Stop Words; The Bag-of-Words Model (BoW); CountVectorizer; Example Problem 1: Spam Detection; Term Frequency Inverse Document Frequency Example Problem 2: Classifying Movie ReviewsSummary; Chapter 4: Topic Modeling and Word Embeddings; Topic Model and Latent Dirichlet Allocation (LDA); Topic Modeling with LDA on Movie Review Data; Non-Negative Matrix Factorization (NMF); Word2Vec; Example Problem 4.2: Training a Word Embedding (Skip-Gram); Continuous Bag-of-Words (CBoW); Example Problem 4.2: Training a Word Embedding (CBoW); Global Vectors for Word Representation (GloVe); Example Problem 4.4: Using Trained Word Embeddings with LSTMs; Paragraph2Vec: Distributed Memory of Paragraph Vectors (PV-DM) Example Problem 4.5: Paragraph2Vec Example with Movie Review DataSummary; Chapter 5: Text Generation, Machine Translation, and Other Recurrent Language Modeling Tasks; Text Generation with LSTMs; Bidirectional RNNs (BRNN); Creating a Name Entity Recognition Tagger; Sequence-to-Sequence Models (Seq2Seq); Question and Answer with Neural Network Models; Summary; Conclusion and Final Statements; Index
• Publisher Details: Berkeley, CA : Apress
• Publication Date: 2018
• Extent: 1 online resource
• Subjects: 006.3/5; Computer science; Natural language processing (Computer science); Python (Computer program language); Machine learning; COMPUTERS / Programming Languages / Python; COMPUTERS / General; Computers -- Programming Languages -- Python; Computers -- Programming -- Open Source; Computers -- Database Management -- General; Programming & scripting languages: general; Computer programming / software development; Databases; Electronic data processing; Python (Computer program language); Open source software; Computer programming; Big data; Computers -- Computer Science; Program concepts / learning to program; Electronic books
• Languages: English
• ISBNs: 9781484237335; 1484237331
• Related ISBNs: 9781484237328
• Notes: Note: Online resource; title from PDF title page (EBSCO, viewed September 18, 2018)
• Access Rights: Legal Deposit; Only available on premises controlled by the deposit library and to one user at any one time; The Legal Deposit Libraries (Non-Print Works) Regulations (UK).
• Access Usage: Restricted: Printing from this resource is governed by The Legal Deposit Libraries (Non-Print Works) Regulations (UK) and UK copyright law currently in force.