Speech and Language Processing
正篇
1.6.1 Foundational Insights: 1940s and 1950s1.6.2 The Two Camps: 1957–19701.6.3 Four Paradigms: 1970–19831.6.4 Empiricism and Finite State Models Redux: 1983–19931.6.5 The Field Comes Together: 1994–19991.6.6 The Rise of Machine Learning: 2000–20071.6.7 On Multiple Discoveries1.6.8 A Final Brief Note on Psychology2.1.1 Basic Regular Expression Patterns2.1.2 Disjunction, Grouping, and Precedence2.1.3 A Simple Example2.1.4 A More Complex Example2.1.5 Advanced Operators2.1.6 Regular Expression Substitution, Memory, and ELIZA2.2.1 Using an FSA to Recognize Sheeptalk2.2.2 Formal Languages2.2.3 Another Example2.2.4 Non-Deterministic FSAs2.2.5 Using an NFSA to Accept Strings2.2.6 Recognition as Search2.2.7 Relating Deterministic and Non-Deterministic Automata3.1.1 Inflectional Morphology3.1.2 Derivational Morphology3.1.3 Cliticization3.1.4 Non-concatenative Morphology3.1.5 Agreement3.4.1 Sequential Transducers and Determinism3.9.1 Segmentation in Chinese4.3.1 N-gram Sensitivity to the Training Corpus4.3.2 Unknown Words: Open versus closed vocabulary tasks4.5.1 Laplace Smoothing4.5.2 Good-Turing Discounting4.5.3 Some advanced issues in Good-Turing estimation4.7.1 Advanced: Details of computing Katz backoff $ \alpha $ and $ P^{*} $4.9.1 Advanced Smoothing Methods: Kneser-Ney Smoothing4.9.2 Class-based N-grams4.9.3 Language Model Adaptation and Using the Web4.9.4 Using Longer Distance Information: A Brief Summary4.10.1 Cross-Entropy for Comparing Models5.5.1 Computing the most-likely tag sequence: A motivating example5.5.2 Formalizing Hidden Markov Model taggers5.5.3 The Viterbi Algorithm for HMM Tagging5.5.4 Extending the HMM algorithm to trigrams5.6.1 How TBL Rules Are Applied5.6.2 How TBL Rules Are Learned5.7.1 Error Analysis5.8.1 Practical Issues: Tag Indeterminacy and Tokenization5.8.2 Unknown Words5.8.3 Part-of-Speech Tagging for Other Languages5.8.4 Combining Taggers5.9.1 Contextual Spelling Error Correction6.6.1 Linear Regression6.6.2 Logistic regression6.6.3 Logistic regression: Classification6.6.4 Advanced: Learning in logistic regression6.7.1 Why do we call it Maximum Entropy?6.8.1 Decoding and Learning in MEMMs7.2.1 The Vocal Organs7.2.2 Consonants: Place of Articulation7.2.3 Consonants: Manner of Articulation7.2.4 Vowels7.3.1 Phonetic Features7.3.2 Predicting Phonetic Variation7.3.3 Factors Influencing Phonetic Variation7.4.1 Waves7.4.2 Speech Sound Waves7.4.3 Frequency and Amplitude; Pitch and Loudness7.4.4 Interpreting Phones from a Waveform7.4.5 Spectra and the Frequency Domain7.4.6 The Source-Filter Model8.1.1 Sentence Tokenization8.1.2 Non-Standard Words8.1.3 Homograph Disambiguation8.2.1 Dictionary Lookup8.2.2 Names8.2.3 Grapheme-to-Phoneme8.3.1 Prosodic Structure8.3.2 Prosodic prominence8.3.3 Tune8.3.4 More sophisticated models: ToBI8.3.5 Computing duration from prosodic labels8.3.6 Computing F0 from prosodic labels8.3.7 Final result of text analysis: Internal Representation8.4.1 Building a diphone database8.4.2 Diphone concatenation and TD-PSOLA for prosodic adjustment9.3.1 Preemphasis9.3.2 Windowing9.3.3 Discrete Fourier Transform9.3.4 Mel filter bank and log9.3.5 The Cepstrum: Inverse Discrete Fourier Transform9.3.6 Deltas and Energy9.3.7 Summary: MFCC9.4.1 Vector Quantization9.4.2 Gaussian PDFs9.4.3 Probabilities, log probabilities and distance functions10.4.1 Maximum Mutual Information Estimation10.4.2 Acoustic Models based on Posterior Classifiers10.5.1 Environmental Variation and Noise10.5.2 Speaker and Dialect Adaptation: Variation due to speaker differences10.5.3 Pronunciation Modeling: Variation due to Genre11.2.1 Harmony11.2.2 Templatic Morphology11.3.1 Finite-State Transducer Models of Optimality Theory11.3.2 Stochastic Models of Optimality Theory11.5.1 Learning Phonological Rules11.5.2 Learning Morphology11.5.3 Learning in Optimality Theory12.2.1 Formal definition of context-free grammar12.3.1 Sentence-Level Constructions12.3.2 Clauses and Sentences12.3.3 The Noun Phrase12.3.4 Agreement12.3.5 The Verb Phrase and Subcategorization12.3.6 Auxiliaries12.3.7 Coordination12.4.1 Example: The Penn Treebank Project12.4.2 Using a Treebank as a Grammar12.4.3 Searching Treebanks12.4.4 Heads and Head Finding12.7.1 The Relationship Between Dependencies and Heads12.7.2 Categorial Grammar12.8.1 Disfluencies and Repair12.8.2 Treebanks for Spoken Language13.1.1 Top-Down Parsing13.1.2 Bottom-Up Parsing13.1.3 Comparing Top-Down and Bottom-Up Parsing13.4.1 CKY Parsing13.4.2 The Earley Algorithm13.4.3 Chart Parsing13.5.1 Finite-State Rule-Based Chunking13.5.2 Machine Learning-Based Approaches to Chunking13.5.3 Evaluating Chunking Systems14.1.1 PCFGs for Disambiguation14.1.2 PCFGs for Language Modeling14.4.1 Independence assumptions miss structural dependencies between rules14.4.2 Lack of sensitivity to lexical dependencies14.6.1 The Collins Parser14.6.2 Advanced: Further Details of the Collins Parser15.2.1 The Pumping Lemma15.2.2 Are English and Other Natural Languages Regular Languages?16.3.1 Agreement16.3.2 Head Features16.3.3 Subcategorization16.3.4 Long-Distance Dependencies16.4.1 Unification Data Structures16.4.2 The Unification Algorithm16.5.1 Integrating Unification into an Earley Parser16.5.2 Unification-Based Parsing16.6.1 Advanced: Extensions to Typing16.6.2 Other Extensions to Unification17.1.1 Verifiability17.1.2 Unambiguous Representations17.1.3 Canonical Form17.1.4 Inference and Variables17.1.5 Expressiveness17.2.1 Predicate-Argument Structure17.4.1 Elements of First Order Logic17.4.2 The Semantics of First Order Logic17.4.3 Variables and Quantifiers17.4.4 Inference17.5.1 Categories17.5.2 Events17.5.3 Representing Time17.5.4 Aspect17.5.5 Representing Beliefs17.5.6 Pitfalls17.6.1 Description Logics17.7.1 Meaning as Action17.7.2 Embodiment as the Basis for Meaning18.3.1 Store and Retrieve Approaches18.3.2 Constraint-Based Approaches18.5.1 Sentences18.5.2 Noun Phrases18.5.3 Verb Phrases18.5.4 Prepositional Phrases19.2.1 Synonymy and Antonymy19.2.2 Hyponymy19.2.3 Semantic Fields19.4.1 Thematic Roles19.4.2 Diathesis Alternations19.4.3 Problems with Thematic Roles19.4.4 The Proposition Bank19.4.5 FrameNet19.4.6 Selectional Restrictions20.2.1 Extracting Feature Vectors for Supervised Learning20.2.2 Naive Bayes and Decision List Classifiers20.4.1 The Lesk Algorithm20.4.2 Selectional Restrictions and Selectional Preferences20.7.1 Defining a Word's Co-occurrence Vectors20.7.2 Measures of Association with Context20.7.3 Defining similarity between two vectors20.7.4 Evaluating Distributional Word Similarity21.1.1 Unsupervised Discourse Segmentation21.1.2 Supervised Discourse Segmentation21.1.3 Evaluating Discourse Segmentation21.2.1 Rhetorical Structure Theory21.2.2 Automatic Coherence Assignment21.4.1 Five Types of Referring Expressions21.4.2 Information Status21.6.1 Pronominal Anaphora Baseline: The Hobbs Algorithm21.6.2 A Centering Algorithm for Anaphora Resolution21.6.3 A Log-Linear model for Pronominal Anaphora Resolution21.6.4 Features21.5 Consider the following passage, from Brennan et al. (1987):21.6 Consider passages (21.100a-b), adapted from Winograd (1972)22.1.1 Ambiguity in Named Entity Recognition22.1.2 NER as Sequence Labeling22.1.3 Evaluating Named Entity Recognition22.1.4 Practical NER Architectures22.2.1 Supervised Learning Approaches to Relation Analysis22.2.2 Lightly Supervised Approaches to Relation Analysis22.2.3 Evaluating Relation Analysis Systems22.3.1 Temporal Expression Recognition22.3.2 Temporal Normalization22.3.3 Event Detection and Analysis22.3.4 TimeBank22.4.2 Finite-State Template-Filling Systems22.5.1 Biological Named Entity Recognition22.5.2 Gene Normalization22.5.3 Biological Roles and Relations23.1.1 The Vector Space Model23.1.2 Term Weighting23.1.3 Term Selection and Creation23.1.4 Evaluating Information Retrieval Systems23.1.5 Homonymy, Polysemy, and Synonymy23.1.6 Improving User Queries23.2.1 Question Processing23.2.2 Passage Retrieval23.2.3 Answer Processing23.2.4 Evaluation of Factoid Answers23.3.1 Summarizing Single Documents23.4.1 Content Selection in Multi-Document Summarization23.4.2 Information Ordering in Multi-Document Summarization24.1.1 Turns and Turn-Taking(24.1) Turn-taking Rule. At each TRP of each turn:24.1.2 Language as Action: Speech Acts24.1.3 Language as Joint Action: Grounding24.1.4 Conversational Structure24.1.5 Conversational Implicature24.2.1 ASR component24.2.2 NLU component24.2.3 Generation and TTS components24.2.4 Dialogue Manager24.2.5 Dialogue Manager Error Handling: Confirmation/Rejection24.4.1 Designing Dialogue Systems24.4.2 Dialogue System Evaluation24.5.1 Dialogue Acts24.5.2 Interpreting Dialogue Acts24.5.3 Detecting Correction Acts24.5.4 Generating Dialogue Acts: Confirmation and Rejection24.7.1 Plan-Inferential Interpretation and Production24.7.2 The Intentional Structure of Dialogue25.1.1 Typology25.1.2 Other Structural Divergences25.1.3 Lexical Divergences25.2.1 Direct Translation