(Ebook) Speech and Language Processing draft 1st Edition by Daniel Jurafsky, James Martin ISBN ‎ 978-0135041963 0135041961

(Ebook) Speech and Language Processing draft 1st Edition by Daniel Jurafsky, James Martin ISBN ‎ 978-0135041963 0135041961

(Ebook) Speech and Language Processing [draft] 1st Edition by Daniel Jurafsky, James H. Martin - Ebook PDF Instant Download/Delivery:  978-0135041963, 0135041961
Full download (Ebook) Speech and Language Processing [draft] 1st Edition  after payment

Product details: 

ISBN 10:   0135041961

ISBN 13: 978-0135041963

Author: Daniel Jurafsky, James H. Martin 

For undergraduate or advanced undergraduate courses in Classical Natural Language Processing, Statistical Natural Language Processing, Speech Recognition, Computational Linguistics, and Human Language Processing.

An explosion of Web-based language techniques, merging of distinct fields, availability of phone-based dialogue systems, and much more make this an exciting time in speech and language processing. The first of its kind to thoroughly cover language technology ― at all levels and with all modern technologies ― this text takes an empirical approach to the subject, based on applying statistical and other machine-learning algorithms to large corporations. The authors cover areas that traditionally are taught in different courses, to describe a unified vision of speech and language processing. Emphasis is on practical applications and scientific evaluation. An accompanying Website contains teaching materials for instructors, with pointers to language processing resources on the Web. The Second Edition offers a significant amount of new and extended material.

Supplements:

Click on the "Resources" tab to View Downloadable Files:

Solutions
Power Point Lecture Slides - Chapters 1-5, 8-10, 12-13 and 24 Now Available!
For additional resourcse visit the author website: http://www.cs.colorado.edu/~martin/slp.html

Table of contents: 

1. Introduction

2. Regular Expressions, Text Normalization, Edit Distance
    2.1 Regular Expressions
    2.2 Basic Regular Expression Patterns
    2.3 Disjunction, Grouping, and Precedence
    2.4 A Simple Example
    2.5 More Operators
    2.6 A More Complex Example
    2.7 Substitution, Capture Groups, and ELIZA
    2.8 Lookahead Assertions
    2.9 Words
    2.10 Corpora
    2.11 Text Normalization
    2.12 Unix Tools for Crude Tokenization and Normalization
    2.13 Word Tokenization
    2.14 Byte-Pair Encoding for Tokenization
    2.15 Word Normalization, Lemmatization and Stemming
    2.16 Sentence Segmentation
    2.17 Minimum Edit Distance
    2.18 The Minimum Edit Distance Algorithm
    2.19 Summary
    2.20 Bibliographical and Historical Notes
    2.21 Exercises

3. N-gram Language Models
    3.1 N-Grams
    3.2 Evaluating Language Models
    3.3 Perplexity
    3.4 Generalization and Zeros
    3.5 Unknown Words
    3.6 Smoothing
     3.6.1 Laplace Smoothing
     3.6.2 Add-k smoothing
     3.6.3 Backoff and Interpolation
     3.6.4 Kneser-Ney Smoothing
     3.6.5 Huge Language Models and Stupid Backoff
    3.7 Advanced: Perplexity's Relation to Entropy
    3.8 Summary
    3.9 Bibliographical and Historical Notes
    3.10 Exercises

4. Naive Bayes and Sentiment Classification
    4.1 Naive Bayes Classifiers
    4.2 Training the Naive Bayes Classifier
    4.3 Worked example
    4.4 Optimizing for Sentiment Analysis
    4.5 Naive Bayes for other text classification tasks
    4.6 Naive Bayes as a Language Model
    4.7 Evaluation: Precision, Recall, F-measure
    4.8 Evaluating with more than two classes
    4.9 Test sets and Cross-validation
    4.10 Statistical Significance Testing
    4.11 The Paired Bootstrap Test
    4.12 Avoiding Harms in Classification
    4.13 Summary
    4.14 Bibliographical and Historical Notes
    4.15 Exercises

5. Logistic Regression
    5.1 Classification: the sigmoid
    5.2 Example: sentiment classification
    5.3 Learning in Logistic Regression
    5.4 The cross-entropy loss function
    5.5 Gradient Descent
    5.6 The Gradient for Logistic Regression
    5.7 The Stochastic Gradient Descent Algorithm
    5.8 Working through an example
    5.9 Mini-batch training
    5.10 Regularization
    5.11 Multinomial logistic regression
    5.12 Features in Multinomial Logistic Regression
    5.13 Learning in Multinomial Logistic Regression
    5.14 Interpreting models
    5.15 Advanced: Deriving the Gradient Equation
    5.16 Summary
    5.17 Bibliographical and Historical Notes
    5.18 Exercises

6. Vector Semantics and Embeddings
    6.1 Lexical Semantics
    6.2 Vector Semantics
    6.3 Words and Vectors
    6.4 Vectors and documents
    6.5 Words as vectors: document dimensions
    6.6 Words as vectors: word dimensions
    6.7 Cosine for measuring similarity
    6.8 TF-IDF: Weighing terms in the vector
    6.9 Pointwise Mutual Information (PMI)
    6.10 Applications of the tf-idf or PPMI vector models
    6.11 Word2vec
    6.12 The classifier
    6.13 Learning skip-gram embeddings
    6.14 Other kinds of static embeddings
    6.15 Visualizing Embeddings
    6.16 Semantic properties of embeddings
    6.17 Embeddings and Historical Semantics
    6.18 Bias and Embeddings
    6.19 Evaluating Vector Models
    6.20 Summary
    6.21 Bibliographical and Historical Notes
    6.22 Exercises

7. Neural Networks and Neural Language Models
    7.1 Units
    7.2 The XOR problem
    7.3 The solution: neural networks
    7.4 Feed-Forward Neural Networks
    7.5 Training Neural Nets
    7.6 Loss function
    7.7 Computing the Gradient
    7.8 Computation Graphs
    7.9 Backward differentiation on computation graphs
    7.10 More details on learning
    7.11 Neural Language Models
    7.12 Embeddings
    7.13 Training the neural language model
    7.14 Summary
    7.15 Bibliographical and Historical Notes

8. Sequence Labeling for Parts of Speech and Named Entities
    8.1 (Mostly) English Word Classes
    8.2 Part-of-Speech Tagging
    8.3 Named Entities and Named Entity Tagging
    8.4 HMM Part-of-Speech Tagging
    8.5 Markov Chains
    8.6 The Hidden Markov Model
    8.7 The components of an HMM tagger
    8.8 HMM tagging as decoding
    8.9 The Viterbi Algorithm
    8.10 Working through an example
    8.11 Conditional Random Fields (CRFs)
    8.12 Features in a CRF POS Tagger
    8.13 Features for CRF Named Entity Recognizers
    8.14 Inference and Training for CRFs
    8.15 Evaluation of Named Entity Recognition
    8.16 Further Details
    8.17 Bidirectionality
    8.18 Rule-based Methods
    8.19 POS Tagging for Morphologically Rich Languages
    8.20 Summary
    8.21 Bibliographical and Historical Notes
    8.22 Exercises

9. Deep Learning Architectures for Sequence Processing
    9.1 Language Models Revisited
    9.2 Recurrent Neural Networks
    9.3 Inference in RNNs
    9.4 Training
    9.5 RNNs as Language Models
    9.6 Other Applications of RNNs
    9.7 RNNs for Sequence Classification
    9.8 Stacked and Bidirectional RNNs
    9.9 Managing Context in RNNs: LSTMs and GRUs
    9.10 Long Short-Term Memory
    9.11 Gated Recurrent Units
    9.12 Gated Units, Layers and Networks
    9.13 Self-Attention Networks: Transformers
    9.14 Transformers as Autoregressive Language Models
    9.15 Potential Harms from Language Models
    9.16 Summary
    9.17 Bibliographical and Historical Notes

10. Contextual Embeddings

11. Machine Translation and Encoder-Decoder Models
     11.1 Language Divergences and Typology
     11.2 Word Order Typology
     11.3 Lexical Divergences
     11.4 Morphological Typology
     11.5 Referential density
     11.6 The Encoder-Decoder Model
     11.7 Encoder-Decoder with RNNs
     11.8 Training the Encoder-Decoder Model
     11.9 Attention
     11.10 Beam Search
     11.11 Encoder-Decoder with Transformers
     11.12 Some practical details on building MT systems
     11.13 Tokenization
     11.14 MT corpora
     11.15 Backtranslation
     11.16 MT Evaluation
     11.17 Using Human Raters to Evaluate MT
     11.18 Automatic Evaluation: BLEU
     11.19 Automatic Evaluation: Embedding-Based Methods
     11.20 Bias and Ethical Issues
     11.21 Summary
     11.22 Bibliographical and Historical Notes
     11.23 Exercises

12. Constituency Grammars
     12.1 Constituency
     12.2 Context-Free Grammars
     12.3 Formal Definition of Context-Free Grammar
     12.4 Some Grammar Rules for English
     12.5 Sentence-Level Constructions
     12.6 Clauses and Sentences
     12.7 The Noun Phrase
     12.8 The Verb Phrase
     12.9 Coordination
     12.10 Treebanks
     12.11 Example: The Penn Treebank Project
     12.12 Treebanks as Grammars
     12.13 Heads and Head Finding
     12.14 Grammar Equivalence and Normal Form
     12.15 Lexicalized Grammars
     12.16 Combinatory Categorial Grammar
     12.17 Summary
     12.18 Bibliographical and Historical Notes
     12.19 Exercises

13. Constituency Parsing
     13.1 Ambiguity
     13.2 CKY Parsing: A Dynamic Programming Approach
     13.3 Conversion to Chomsky Normal Form
     13.4 CKY Recognition
     13.5 CKY Parsing
     13.6 CKY in Practice
     13.7 Span-Based Neural Constituency Parsing
     13.8 Computing Scores for a Span
     13.9 Integrating Span Scores into a Parse
     13.10 Evaluating Parsers
     13.11 Partial Parsing
     13.12 CCG Parsing
     13.13 Ambiguity in CCG
     13.14 CCG Parsing Frameworks
     13.15 Supertagging
     13.16 CCG Parsing using the A* Algorithm
     13.17 Summary
     13.18 Bibliographical and Historical Notes
     13.19 Exercises

14. Dependency Parsing
     14.1 Dependency Relations
     14.2 Dependency Formalisms
     14.3 Projectivity
     14.4 Dependency Treebanks
     14.5 Transition-Based Dependency Parsing
     14.6 Creating an Oracle
     14.7 Advanced Methods in Transition-Based Parsing
     14.8 Graph-Based Dependency Parsing
     14.9 Parsing
     14.10 Features and Training
     14.11 Advanced Issues in Graph-Based Parsing
     14.12 Evaluation
     14.13 Summary
     14.14 Bibliographical and Historical Notes
     14.15 Exercises

15. Logical Representations of Sentence Meaning
     15.1 Computational Desiderata for Representations
     15.2 Model-Theoretic Semantics
     15.3 First-Order Logic
     15.4 Basic Elements of First-Order Logic
     15.5 Variables and Quantifiers
     15.6 Lambda Notation
     15.7 The Semantics of First-Order Logic
     15.8 Inference
     15.9 Event and State Representations
     15.10 Representing Time
     15.11 Aspect
     15.12 Description Logics
     15.13 Summary
     15.14 Bibliographical and Historical Notes
     15.15 Exercises

16. Computational Semantics and Semantic Parsing
     16.1 Information Extraction
     16.2 Relation Extraction
     16.3 Relation Extraction Algorithms
     16.4 Using Patterns to Extract Relations
     16.5 Relation Extraction via Supervised Learning
     16.6 Semisupervised Relation Extraction via Bootstrapping
     16.7 Distant Supervision for Relation Extraction
     16.8 Unsupervised Relation Extraction
     16.9 Evaluation of Relation Extraction
     16.10 Extracting Times
     16.11 Temporal Expression Extraction
     16.12 Temporal Normalization
     16.13 Extracting Events and their Times
     16.14 Temporal Ordering of Events
     16.15 Template Filling
     16.16 Machine Learning Approaches to Template Filling
     16.17 Earlier Finite-State Template-Filling Systems
     16.18 Summary
     16.19 Bibliographical and Historical Notes
     16.20 Exercises

17. Word Senses and WordNet
     17.1 Word Senses
     17.2 Defining Word Senses
     17.3 How many senses do words have?
     17.4 Relations Between Senses
     17.5 WordNet: A Database of Lexical Relations
     17.6 Sense Relations in WordNet
     17.7 Word Sense Disambiguation
     17.8 WSD: The Task and Datasets
     17.9 The WSD Algorithm: Contextual Embeddings
     17.10 Alternate WSD algorithms and Tasks
     17.11 Feature-Based WSD
     17.12 The Lesk Algorithm as WSD Baseline
     17.13 Word-in-Context Evaluation
     17.14 Wikipedia as a source of training data
     17.15 Using Thesauruses to Improve Embeddings
     17.16 Word Sense Induction
     17.17 Summary
     17.18 Bibliographical and Historical Notes
     17.19 Exercises

18. Semantic Role Labeling
     18.1 Semantic Roles
     18.2 Diathesis Alternations
     18.3 Semantic Roles: Problems with Thematic Roles
     18.4 The Proposition Bank
     18.5 FrameNet
     18.6 Semantic Role Labeling
     18.7 A Feature-based Algorithm for Semantic Role Labeling
     18.8 A Neural Algorithm for Semantic Role Labeling
     18.9 Evaluation of Semantic Role Labeling
     18.10 Selectional Restrictions
     18.11 Representing Selectional Restrictions
     18.12 Selectional Preferences
     18.13 Primitive Decomposition of Predicates
     18.14 Summary
     18.15 Bibliographical and Historical Notes
     18.16 Exercises

19. Lexicons for Sentiment, Affect, and Connotation
     19.1 Defining Emotion
     19.2 Available Sentiment and Affect Lexicons
     19.3 Creating Affect Lexicons by Human Labeling
     19.4 Semi-supervised Induction of Affect Lexicons
     19.5 Semantic Axis Methods
     19.6 Label Propagation
     19.7 Other Methods
     19.8 Supervised Learning of Word Sentiment
     19.9 Log Odds Ratio Informative Dirichlet Prior
     19.10 Using Lexicons for Sentiment Recognition
     19.11 Other tasks: Personality
     19.12 Affect Recognition
     19.13 Lexicon-based methods for Entity-Centric Affect
     19.14 Connotation Frames
     19.15 Summary
     19.16 Bibliographical and Historical Notes

20. Coreference Resolution
     20.1 Coreference Phenomena: Linguistic Background
     20.2 Types of Referring Expressions
     20.3 Information Status
     20.4 Complications: Non-Referring Expressions
     20.5 Linguistic Properties of the Coreference Relation
     20.6 Coreference Tasks and Datasets
     20.7 Mention Detection
     20.8 Architectures for Coreference Algorithms
     20.9 The Mention-Pair Architecture
     20.10 The Mention-Rank Architecture
     20.11 Entity-based Models
     20.12 Classifiers using hand-built features
     20.13 A neural mention-ranking algorithm
     20.14 Evaluation of Coreference Resolution
     20.15 Winograd Schema problems
     20.16 Gender Bias in Coreference
     20.17 Summary
     20.18 Bibliographical and Historical Notes
     20.19 Exercises

21. Discourse Coherence
     21.1 Coherence Relations
     21.2 Rhetorical Structure Theory
     21.3 Penn Discourse TreeBank (PDTB)
     21.4 Discourse Structure Parsing
     21.5 EDU segmentation for RST parsing
     21.6 RST parsing
     21.7 PDTB discourse parsing
     21.8 Centering and Entity-Based Coherence
     21.9 Centering
     21.10 Entity Grid model

People also search for:

speech and language pathologist salary
    
speech and language center
    
speech and language disorders
    
speech and language at home
    
speech and language assessments

Tags: Daniel Jurafsky, James Martin, Speech and Language, Processing draft