| |
| |
| Foreword | |
| |
| |
| Preface | |
| |
| |
| About the Authors | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Knowledge in Speech and Language Processing | |
| |
| |
| |
| Ambiguity | |
| |
| |
| |
| Models and Algorithms | |
| |
| |
| |
| Language, Thought, and Understanding | |
| |
| |
| |
| The State of the Art | |
| |
| |
| |
| Some Brief History | |
| |
| |
| |
| Foundational Insights: 1940s and 1950s | |
| |
| |
| |
| The Two Camps: 1957 1970 | |
| |
| |
| |
| Four Paradigms: 1970 1983 | |
| |
| |
| |
| Empiricism and Finite State Models Redux: 1983 1993 | |
| |
| |
| |
| The Field Comes Together: 1994 1999 | |
| |
| |
| |
| The Rise of Machine Learning: 2000 2008 | |
| |
| |
| |
| On Multiple Discoveries | |
| |
| |
| |
| A Final Brief Note on Psychology | |
| |
| |
| |
| SummaryBibliographical and Historical Notes | |
| |
| |
| |
| Words2 Regular Expressions and Automata | |
| |
| |
| |
| Regular Expressions | |
| |
| |
| |
| Basic Regular Expression Patterns | |
| |
| |
| |
| Disjunction, Grouping, and Precedence | |
| |
| |
| |
| A Simple Example | |
| |
| |
| |
| A More Complex Example | |
| |
| |
| |
| Advanced Operators | |
| |
| |
| |
| Regular Expression Substitution, Memory, and ELIZA | |
| |
| |
| |
| Finite-State Automata | |
| |
| |
| |
| Using an FSA to Recognize Sheeptalk | |
| |
| |
| |
| Formal Languages | |
| |
| |
| |
| Another Example | |
| |
| |
| |
| Non-Deterministic FSAs | |
| |
| |
| |
| Using an NFSA to Accept Strings | |
| |
| |
| |
| Recognition as Search | |
| |
| |
| |
| Relating Deterministic and Non-Deterministic Automata | |
| |
| |
| |
| Regular Languages and FSAs | |
| |
| |
| |
| SummaryBibliographical and Historical NotesExercises3 Words and Transducers | |
| |
| |
| |
| Survey of (Mostly) English Morphology | |
| |
| |
| |
| Inflectional Morphology | |
| |
| |
| |
| Derivational Morphology | |
| |
| |
| |
| Cliticization | |
| |
| |
| |
| Non-Concatenative Morphology | |
| |
| |
| |
| Agreement | |
| |
| |
| |
| Finite-State Morphological Parsing | |
| |
| |
| |
| Construction of a Finite-State Lexicon | |
| |
| |
| |
| Finite-State Transducers | |
| |
| |
| |
| Sequential Transducers and Determinism | |
| |
| |
| |
| FSTs for Morphological Parsing | |
| |
| |
| |
| Transducers and Orthographic Rules | |
| |
| |
| |
| The COmbination of an FST Lexicon and Rules | |
| |
| |
| |
| Lexicon-Free FSTs: The Porter Stemmer | |
| |
| |
| |
| Word and Sentence Tokenization | |
| |
| |
| |
| Segmentation in Chinese | |
| |
| |
| |
| Detection and Correction of Spelling Errors | |
| |
| |
| |
| Minimum Edit Distance | |
| |
| |
| |
| Human Morphological Processing | |
| |
| |
| |
| SummaryBibliographical and Historical NotesExercises4 N-grams | |
| |
| |
| |
| Word Counting in Corpora | |
| |
| |
| |
| Simple (Unsmoothed) N-grams | |
| |
| |
| |
| Training and Test Sets | |
| |
| |
| |
| N-gram Sensitivity to the Training Corpus | |
| |
| |
| |
| Unknown Words: Open Versus Closed Vocabulary Tasks | |
| |
| |
| |
| Evaluating N-grams: Perplexity | |
| |
| |
| |
| Smoothing | |
| |
| |
| |
| Laplace Smoothing | |
| |
| |
| |
| Good-Turing Discounting | |
| |
| |
| |
| Some Advanced Issues in Good-Turing Estimation | |
| |
| |
| |
| Interpolation | |
| |
| |
| |
| Backoff | |
| |
| |
| |
| Advanced: Details of Computing Katz Backoff a and P | |
| |
| |
| |
| Practical Issues: Toolkits and Data Formats | |
| |
| |
| |
| Advanced Issues in Language Modeling | |
| |
| |
| |
| Advanced Smoothing Methods: Kneser-Ney Smoothing | |
| |
| |
| |
| Class-Based N-grams | |
| |
| |
| |
| Language Model Adaptation and Web Use | |
| |
| |
| |
| Using Longer Distance Information: A Brief Summary | |
| |
| |
| |
| Advanced: Information Theory Background | |
| |
| |
| |
| Cross-Entropy for Comparing Models | |
| |
| |
| |
| Advanced: The Entropy of English and Entropy Rate Constancy | |
| |
| |
| |
| SummaryBibliographical and Historical NotesExercises5 Part-of-Speech Tagging | |
| |
| |
| |
| (Mostly) English Word Classes | |
| |
| |
| |
| Tagsets for English | |
| |
| |
| |
| Part-of-Speech Tagging | |
| |
| |
| |
| Rule-Based Part-of-Speech Tagging | |
| |
| |
| |
| HMM Part-of-Speech Tagging | |
| |
| |
| |
| Computing the Most-Likely Tag Sequence: An Example | |