| An Overview of Language Processing / 1： |
| Linguistics and Language Processing / 1.1： |
| Applications of Language Processing / 1.2： |
| The Different Domains of Language Processing / 1.3： |
| Phonetics / 1.4： |
| Lexicon and Morphology / 1.5： |
| Syntax / 1.6： |
| Syntax as Defined by Noam Chomsky / 1.6.1： |
| Syntax as Relations and Dependencies / 1.6.2： |
| Semantics / 1.7： |
| Discourse and Dialogue / 1.8： |
| Why Speech and Language Processing Are Difficult / 1.9： |
| Ambiguity / 1.9.1： |
| Models and Their Implementation / 1.9.2： |
| An Example of Language Technology in Action: the Persona Project / 1.10： |
| Overview of Persona / 1.10.1： |
| The Persona's Modules / 1.10.2： |
| Further Reading / 1.11： |
| Corpus Processing Tools / 2： |
| Corpora / 2.1： |
| Types of Corpora / 2.1.1： |
| Corpora and Lexicon Building / 2.1.2： |
| Corpora as Knowledge Sources for the Linguist / 2.1.3： |
| Finite-State Automata / 2.2： |
| A Description / 2.2.1： |
| Mathematical Definition of Finite-State Automata / 2.2.2： |
| Finite-State Automata in Prolog / 2.2.3： |
| Deterministic and Nondeterministic Automata / 2.2.4： |
| Building a Deterministic Automata from a Nondeterministic One / 2.2.5： |
| Searching a String with a Finite-State Automaton / 2.2.6： |
| Operations on Finite-State Automata / 2.2.7： |
| Regular Expressions / 2.3： |
| Repetition Metacharacters / 2.3.1： |
| The Longest Match / 2.3.2： |
| Character Classes / 2.3.3： |
| Nonprintable Symbols or Positions / 2.3.4： |
| Union and Boolean Operators / 2.3.5： |
| Operator Combination and Precedence / 2.3.6： |
| Programming with Regular Expressions / 2.4： |
| Perl / 2.4.1： |
| Matching / 2.4.2： |
| Substitutions / 2.4.3： |
| Translating Characters / 2.4.4： |
| String Operators / 2.4.5： |
| Back References / 2.4.6： |
| Finding Concordances / 2.5： |
| Concordances in Prolog / 2.5.1： |
| Concordances in Perl / 2.5.2： |
| Approximate String Matching / 2.6： |
| Edit Operations / 2.6.1： |
| Minimum Edit Distance / 2.6.2： |
| Searching Edits in Prolog / 2.6.3： |
| Encoding, Entropy, and Annotation Schemes / 2.7： |
| Encoding Texts / 3.1： |
| Character Sets / 3.2： |
| Representing Characters / 3.2.1： |
| Unicode / 3.2.2： |
| The Unicode Encoding Schemes / 3.2.3： |
| Locales and Word Order / 3.3： |
| Presenting Time, Numerical Information, and Ordered Words / 3.3.1： |
| The Unicode Collation Algorithm / 3.3.2： |
| Markup Languages / 3.4： |
| A Brief Background / 3.4.1： |
| An Outline of XML / 3.4.2： |
| Writing a DTD / 3.4.3： |
| Writing an XML Document / 3.4.4： |
| Namespaces / 3.4.5： |
| Codes and Information Theory / 3.5： |
| Entropy / 3.5.1： |
| Huffman Encoding / 3.5.2： |
| Cross Entropy / 3.5.3： |
| Perplexity and Cross Perplexity / 3.5.4： |
| Entropy and Decision Trees / 3.6： |
| Decision Trees / 3.6.1： |
| Inducing Decision Trees Automatically / 3.6.2： |
| Counting Words / 3.7： |
| Counting Words and Word Sequences / 4.1： |
| Words and Tokens / 4.2： |
| What Is a Word? / 4.2.1： |
| Breaking a Text into Words: Tokenization / 4.2.2： |
| Tokenizing Texts / 4.3： |
| Tokenizing Texts in Prolog / 4.3.1： |
| Tokenizing Texts in Perl / 4.3.2： |
| N-grams / 4.4： |
| Some Definitions / 4.4.1： |
| Counting Unigrams in Prolog / 4.4.2： |
| Counting Unigrams with Perl / 4.4.3： |
| Counting Bigrams with Perl / 4.4.4： |
| Probabilistic Models of a Word Sequence / 4.5： |
| The Maximum Likelihood Estimation / 4.5.1： |
| Using ML Estimates with Nineteen Eighty-Four / 4.5.2： |
| Smoothing N-gram Probabilities / 4.6： |
| Sparse Data / 4.6.1： |
| Laplace's Rule / 4.6.2： |
| Good-Turing Estimation / 4.6.3： |
| Using N-grams of Variable Length / 4.7： |
| Linear Interpolation / 4.7.1： |
| Back-off / 4.7.2： |
| Quality of a Language Model / 4.8： |
| Intuitive Presentation / 4.8.1： |
| Entropy Rate / 4.8.2： |
| Perplexity / 4.8.3： |
| Collocations / 4.9： |
| Word Preference Measurements / 4.9.1： |
| Extracting Collocations with Perl / 4.9.2： |
| Application: Retrieval and Ranking of Documents on the Web / 4.10： |
| Words, Parts of Speech, and Morphology / 4.11： |
| Words / 5.1： |
| Parts of Speech / 5.1.1： |
| Features / 5.1.2： |
| Two Significant Parts of Speech: The Noun and the Verb / 5.1.3： |
| Lexicons / 5.2： |
| Encoding a Dictionary / 5.2.1： |
| Building a Trie in Prolog / 5.2.2： |
| Finding a Word in a Trie / 5.2.3： |
| Morphology / 5.3： |
| Morphemes / 5.3.1： |
| Morphs / 5.3.2： |
| Inflection and Derivation / 5.3.3： |
| Language Differences / 5.3.4： |
| Morphological Parsing / 5.4： |
| Two-Level Model of Morphology / 5.4.1： |
| Interpreting the Morphs / 5.4.2： |
| Finite-State Transducers / 5.4.3： |
| Conjugating a French Verb / 5.4.4： |
| Prolog Implementation / 5.4.5： |
| Operations on Finite-State Transducers / 5.4.6： |
| Morphological Rules / 5.5： |
| Two-Level Rules / 5.5.1： |
| Rules and Finite-State Transducers / 5.5.2： |
| Rule Composition: An Examplewith French Irregular Verbs / 5.5.3： |
| Application Examples / 5.6： |
| Part-of-Speech Tagging Using Rules / 5.7： |
| Resolving Part-of-Speech Ambiguity / 6.1： |
| A Manual Method / 6.1.1： |
| Which Method to Use to Automatically Assign Parts of Speech / 6.1.2： |
| Tagging with Rules / 6.2： |
| Brill's Tagger / 6.2.1： |
| Implementation in Prolog / 6.2.2： |
| Deriving Rules Automatically / 6.2.3： |
| Confusion Matrices / 6.2.4： |
| Unknown Words / 6.3： |
| Standardized Part-of-Speech Tagsets / 6.4： |
| Multilingual Part-of-Speech Tags / 6.4.1： |
| Parts of Speechfor English / 6.4.2： |
| An Annotation Schemefor Swedish / 6.4.3： |
| Part-of-Speech Tagging Using Stochastic Techniques / 6.5： |
| The Noisy Channel Model / 7.1： |
| Presentation / 7.1.1： |
| The N-gram Approximation / 7.1.2： |
| Tagging a Sentence / 7.1.3： |
| The Viterbi Algorithm: An Intuitive Presentation / 7.1.4： |
| Markov Models / 7.2： |
| Markov Chains / 7.2.1： |
| Hidden Markov Models / 7.2.2： |
| Three Fundamental Algorithms to Solve Problems with HMMs / 7.2.3： |
| The Forward Procedure / 7.2.4： |
| Viterbi Algorithm / 7.2.5： |
| The Backward Procedure / 7.2.6： |
| The Forward-Backward Algorithm / 7.2.7： |
| Tagging with Decision Trees / 7.3： |
| An Application of the Noisy Channel Model: Spell Checking / 7.4： |
| A Second Application: Language Models for Machine Translation / 7.6： |
| Parallel Corpora / 7.6.1： |
| Alignment / 7.6.2： |
| Translation / 7.6.3： |
| Phrase-Structure Grammars in Prolog / 7.7： |
| Using Prolog to Write Phrase-Structure Grammars / 8.1： |
| Representing Chomsky's Syntactic Formalism in Prolog / 8.2： |
| Constituents / 8.2.1： |
| Tree Structures / 8.2.2： |
| Phrase-Structure Rules / 8.2.3： |
| The Definite Clause Grammar (DCG) Notation / 8.2.4： |
| Parsing with DCGs / 8.3： |
| Translating DCGs into Prolog Clauses / 8.3.1： |
| Parsing and Generation / 8.3.2： |
| Left-Recursive Rules / 8.3.3： |
| Parsing Ambiguity / 8.4： |
| Using Variables / 8.5： |
| Gender and Number Agreement / 8.5.1： |
| Obtaining the Syntactic Structure / 8.5.2： |
| Application: Tokenizing Texts Using DCG Rules / 8.6： |
| Word Breaking / 8.6.1： |
| Recognition of Sentence Boundaries / 8.6.2： |
| Semantic Representation / 8.7： |
| A-Calculus / 8.7.1： |
| Embedding A-Expressions into DCG Rules / 8.7.2： |
| Semantic Composition of Verbs / 8.7.3： |
| An Application of Phrase-Structure Grammars and a Worked Example / 8.8： |
| Partial Parsing / 8.9： |
| Is Syntax Necessary? / 9.1： |
| Word Spotting and Template Matching / 9.2： |
| ELIZA / 9.2.1： |
| Word Spotting in Prolog / 9.2.2： |
| Multiword Detection / 9.3： |
| Multiwords / 9.3.1： |
| AStandard Multiword Annotation / 9.3.2： |
| Detecting Multiwords with Rules / 9.3.3： |
| Running the Program / 9.3.4： |
| Noun Groups and Verb Groups / 9.4： |
| Groups Versus Recursive Phrases / 9.4.1： |
| DCG Rules to Detect Noun Groups / 9.4.2： |
| DCG Rules to Detect Verb Groups / 9.4.3： |
| Running the Rules / 9.4.4： |
| Group Detection as a Tagging Problem / 9.5： |
| Tagging Gaps / 9.5.1： |
| Tagging Words / 9.5.2： |
| Using Symbolic Rules / 9.5.3： |
| Using Statistical Tagging / 9.5.4： |
| Cascading Partial Parsers / 9.6： |
| Elementary Analysis of Grammatical Functions / 9.7： |
| Main Functions / 9.7.1： |
| Extracting Other Groups / 9.7.2： |
| An Annotation Scheme for Groups in French / 9.8： |
| Application: The FASTUS System / 9.9： |
| The Message Understanding Conferences / 9.9.1： |
| The Syntactic Layers of the FASTUS System / 9.9.2： |
| Evaluationof Information Extraction Systems / 9.9.3： |
| Syntactic Formalisms / 9.10： |
| Introduction / 10.1： |
| Chomsky's Grammar in Syntactic Structures / 10.2： |
| Constituency: A Formal Definition / 10.2.1： |
| Transformations / 10.2.2： |
| Transformations and Movements / 10.2.3： |
| Gap Threading / 10.2.4： |
| Gap Threading to Parse Relative Clauses / 10.2.5： |
| Standardized Phrase Categories for English / 10.3： |
| Unification-Based Grammars / 10.4： |
| Representing Features in Prolog / 10.4.1： |
| A Formalism for Features and Rules / 10.4.3： |
| Features Organization / 10.4.4： |
| Features and Unification / 10.4.5： |
| A Unification Algorithm for Feature Structures / 10.4.6： |
| Dependency Grammars / 10.5： |
| Properties of a Dependency Graph / 10.5.1： |
| Valence / 10.5.3： |
| Dependencies and Functions / 10.5.4： |
| Parsing Techniques / 10.6： |
| Bottom-up Parsing / 11.1： |
| The Shift-Reduce Algorithm / 11.2.1： |
| Implementing Shift-Reduce Parsing in Prolog / 11.2.2： |
| Differences Between Bottom-up and Top-down Parsing / 11.2.3： |
| Chart Parsing / 11.3： |
| Backtracking and Efficiency / 11.3.1： |
| Structure of a Chart / 11.3.2： |
| The Active Chart / 11.3.3： |
| Modules of an Earley Parser / 11.3.4： |
| The Earley Algorithm in Prolog / 11.3.5： |
| The Earley Parser to Handle Left-Recursive Rules and Empty Symbols / 11.3.6： |
| Probabilistic Parsing of Context-Free Grammars / 11.4： |
| A Description of PCFGs / 11.5： |
| The Bottom-up Chart / 11.5.1： |
| The Cocke-Younger-Kasami Algorithm in Prolog / 11.5.2： |
| Adding Probabilities to the CYK Parser / 11.5.3： |
| Parser Evaluation / 11.6： |
| Constituency-Based Evaluation / 11.6.1： |
| Dependency-Based Evaluation / 11.6.2： |
| PerformanceofPCFG Parsing / 11.6.3： |
| Parsing Dependencies / 11.7： |
| Dependency Rules / 11.7.1： |
| Extending the Shift-Reduce Algorithm to Parse Dependencies / 11.7.2： |
| Nivre's Parser in Prolog / 11.7.3： |
| Finding Dependencies Using Constraints / 11.7.4： |
| Parsing Dependencies Using Statistical Techniques / 11.7.5： |
| Semantics and Predicate Logic / 11.8： |
| Language Meaning and Logic: An Illustrative Example / 12.1： |
| Formal Semantics / 12.3： |
| First-Order Predicate Calculus to Represent the State of Affairs / 12.4： |
| Variables and Constants / 12.4.1： |
| Predicates / 12.4.2： |
| Querying the Universe of Discourse / 12.5： |
| Mapping Phrases onto Logical Formulas / 12.6： |
| Representing Nouns and Adjectives / 12.6.1： |
| Representing Noun Groups / 12.6.2： |
| Representing Verbs and Prepositions / 12.6.3： |
| The Case of Determiners / 12.7： |
| Determiners and Logic Quantifiers / 12.7.1： |
| Translating Sentences Using Quantifiers / 12.7.2： |
| A General Representation of Sentences / 12.7.3： |
| Compositionality to Translate Phrases to Logical Forms / 12.8： |
| Translating the Noun Phrase / 12.8.1： |
| Translating the Verb Phrase / 12.8.2： |
| Augmenting the Database and Answering Questions / 12.9： |
| Declarations / 12.9.1： |
| Questions with Existential and Universal Quantifiers / 12.9.2： |
| Prolog and Unknown Predicates / 12.9.3： |
| Other Determiners and Questions / 12.9.4： |
| Application: The Spoken Language Translator / 12.10： |
| Translating Spoken Sentences / 12.10.1： |
| Compositional Semantics / 12.10.2： |
| Semantic Representation Transfer / 12.10.3： |
| Lexical Semantics / 12.11： |
| Beyond Formal Semantics / 13.1： |
| La langue etlaparole / 13.1.1： |
| Language and the Structure of the World / 13.1.2： |
| Lexical Structures / 13.2： |
| Some Basic Terms and Concepts / 13.2.1： |
| Ontological Organization / 13.2.2： |
| Lexical Classes and Relations / 13.2.3： |
| Semantic Networks / 13.2.4： |
| Building a Lexicon / 13.3： |
| The Lexicon and Word Senses / 13.3.1： |
| Verb Models / 13.3.2： |
| Definitions / 13.3.3： |
| An Example of Exhaustive Lexical Organization: Word Net / 13.4： |
| Nouns / 13.4.1： |
| Adjectives / 13.4.2： |
| Verbs / 13.4.3： |
| Automatic Word Sense Disambiguation / 13.5： |
| Senses as Tags / 13.5.1： |
| Associating a Word with a Context / 13.5.2： |
| Guessing the Topic / 13.5.3： |
| Naive Bayes / 13.5.4： |
| Using Constraints on Verbs / 13.5.5： |
| Using Dictionary Definitions / 13.5.6： |
| An Unsupervised Algorithm to Tag Senses / 13.5.7： |
| Senses and Languages / 13.5.8： |
| Case Grammars / 13.6： |
| Cases in Latin / 13.6.1： |
| Cases and Thematic Roles / 13.6.2： |
| Parsing with Cases / 13.6.3： |
| Semantic Grammars / 13.6.4： |
| Extending Case Grammars / 13.7： |
| Frame Net / 13.7.1： |
| A Statistical Method to Identify Semantic Roles / 13.7.2： |
| An Example of Case Grammar Application: EVAR / 13.8： |
| EVAR's Ontology and Syntactic Classes / 13.8.1： |
| Cases in EVAR / 13.8.2： |
| Discourse / 13.9： |
| Discourse: A Minimalist Definition / 14.1： |
| A Description of Discourse / 14.2.1： |
| Discourse Entities / 14.2.2： |
| References: An Application-Oriented View / 14.3： |
| References and Noun Phrases / 14.3.1： |
| Finding Names - Proper Nouns / 14.3.2： |
| Coreference / 14.4： |
| Anaphora / 14.4.1： |
| Solving Coreferences in an Example / 14.4.2： |
| A Standard Coreference Annotation / 14.4.3： |
| References: A More Formal View / 14.5： |
| Generating Discourse Entities: The Existential Quantifier / 14.5.1： |
| Retrieving Discourse Entities: Definite Descriptions / 14.5.2： |
| Generating Discourse Entities: The Universal Quantifier / 14.5.3： |
| Centering: A Theory on Discourse Structure / 14.6： |
| Solving Coreferences / 14.7： |
| A Simplistic Method: Using Syntactic and Semantic Compatibility / 14.7.1： |
| Solving Coreferences with Shallow Grammatical Information / 14.7.2： |
| Salience in a Multimodal Context / 14.7.3： |
| Using a Machine-Learning Technique to Resolve Coreferences / 14.7.4： |
| More Complex Phenomena: Ellipses / 14.7.5： |
| Discourse and Rhetoric / 14.8： |
| Ancient Rhetoric: An Outline / 14.8.1： |
| Rhetorical Structure Theory / 14.8.2： |
| Types of Relations / 14.8.3： |
| Implementing Rhetorical Structure Theory / 14.8.4： |
| Events and Time / 14.9： |
| Events / 14.9.1： |
| Event Types / 14.9.2： |
| Temporal Representation of Events / 14.9.3： |
| Events and Tenses / 14.9.4： |
| Time ML, an Annotation Scheme for Time and Events / 14.10： |
| Dialogue / 14.11： |
| Why a Dialogue? / 15.1： |
| Simple Dialogue Systems / 15.3： |
| Dialogue Systems Based on Automata / 15.3.1： |
| Dialogue Modeling / 15.3.2： |
| Speech Acts: A Theory of Language Interaction / 15.4： |
| Speech Acts and Human-Machine Dialogue / 15.5： |
| Speech Acts as a Tagging Model / 15.5.1： |
| Speech Acts Tags Used in the SUNDIAL Project / 15.5.2： |
| Dialogue Parsing / 15.5.3： |
| Interpreting Speech Acts / 15.5.4： |
| EVAR: A Dialogue Application Using Speech Acts / 15.5.5： |
| Taking Beliefs and Intentions into Account / 15.6： |
| Representing Mental States / 15.6.1： |
| The STRIPS Planning Algorithm / 15.6.2： |
| Causality / 15.6.3： |
| An Introduction to Prolog / 15.7： |
| A Short Background / A.1： |
| Basic Features of Prolog / A.2： |
| Facts / A.2.1： |
| Terms / A.2.2： |
| Queries / A.2.3： |
| Logical Variables / A.2.4： |
| Shared Variables / A.2.5： |
| Data Types in Prolog / A.2.6： |
| Rules / A.2.7： |
| Running a Program / A.3： |
| Unification / A.4： |
| Substitution and Instances / A.4.1： |
| Terms and Unification / A.4.2： |
| The Herbrand Unification Algorithm / A.4.3： |
| Example / A.4.4： |
| The Occurs-Check / A.4.5： |
| Resolution / A.5： |
| Modus Ponens / A.5.1： |
| A Resolution Algorithm / A.5.2： |
| Derivation Trees and Backtracking / A.5.3： |
| Tracing and Debugging / A.6： |
| Cuts, Negation, and Related Predicates / A.7： |
| Cuts / A.7.1： |
| Negation / A.7.2： |
| The once/1 Predicate / A.7.3： |
| Lists / A.8： |
| Some List-Handling Predicates / A.9： |
| The member/2 Predicate / A.9.1： |
| The append/3 Predicate / A.9.2： |
| The delete/3 Predicate / A.9.3： |
| The intersection/3 Predicate / A.9.4： |
| The reverse/2 Predicate / A.9.5： |
| The Mode of an Argument / A.9.6： |
| Operators and Arithmetic / A.10： |
| Operators / A.10.1： |
| Arithmetic Operations / A.10.2： |
| Comparison Operators / A.10.3： |
| Lists and Arithmetic: The length/2 Predicate / A.10.4： |
| Lists and Comparison: The quicksort/2 Predicate / A.10.5： |
| Some Other Built-in Predicates / A.11： |
| Type Predicates / A.11.1： |
| Term Manipulation Predicates / A.11.2： |
| Handling Run-Time Errors and Exceptions / A.12： |
| Dynamically Accessing and Updatingthe Database / A.13： |
| Accessing a Clause: The clause/2 Predicate / A.13.1： |
| Dynamic and Static Predicates / A.13.2： |
| Adding a Clause: The asserta/1 and 1 assertz/Predicates / A.13.3： |
| Removing Clauses: The retract/1 and abolish/2 Predicates / A.13.4： |
| Handling Unknown Predicates / A.13.5： |
| All-Solutions Predicates / A.14： |
| Fundamental Search Algorithms / A.15： |
| Representing the Graph / A.15.1： |
| Depth-First Search / A.15.2： |
| Breadth-First Search / A.15.3： |
| A* Search / A.15.4： |
| Input/Output / A.16： |
| Reading and Writing Characters with Edinburgh Prolog / A.16.1： |
| Reading and Writing Terms with Edinburgh Prolog / A.16.2： |
| Opening and Closing Files with Edinburgh Prolog / A.16.3： |
| Reading and Writing Characters with Standard Prolog / A.16.4： |
| Reading and Writing Terms with Standard Prolog / A.16.5： |
| Opening and Closing Files with Standard Prolog / A.16.6： |
| Writing Loops / A.16.7： |
| Developing Prolog Programs / A.17： |
| Presentation Style / A.17.1： |
| Improving Programs / A.17.2： |
| Index |
| References |
ＥＢ
