• Index

    Index

    • _

      • (phrasal) projections (3.2)

    • A

      • accuracy (3.2)
      • address (4.5)
      • adjectives (2.6)
      • adverbs (2.6)
      • agreement (1.1)
      • alphabetic variants (4.2)
      • anaphora resolution (5.2)
      • anaphoric antecedent (5.1)
      • antecedent (5.2)
      • antonymy (5.3)
      • appending (2.1)
      • appropriate (5)
      • argument (2)
      • arity (3.3)
      • articles (2.6)
      • assignment (3.5)
      • associative array (3)
      • assumption (2)
      • atomic (1.3)
      • attribute value matrix (1.3)
      • auxiliaries (3.3)
      • auxiliary (1.3)

    • B

      • backoff (4.3)
      • backtracks (4.1)
      • base case (4.7.1)
      • basic types (3.1)
      • bigrams (3.3)
      • binary predicate (3.1)
      • bind (3.1)
      • binding operators (4.5)
      • binning (5.3)
      • BIO Format (8)
      • Bold (X)
      • boolean (1.3)
      • boolean operators (2)
      • bottom-up (4.7.3)
      • bottom-up parsing (4.1)
      • bound (3.1)
      • bound (3.1)
      • breakpoints (4.6.4)

    • C

      • call-by-value (4.4.2)
      • call (1.4)
      • call structure (4.7.3)
      • Catalan numbers (6.2)
      • characteristic function (3.4)
      • chart (4.4)
      • chart parsing (4.4)
      • child (4.2)
      • chink (2.5)
      • chink (8)
      • chunk grammar (2.1)
      • chunk (2)
      • chunking (2)
      • class label (1)
      • Classification (1)
      • closed class (7.4)
      • closed (3.1)
      • closures (3.4.2)
      • code point (3.3.1)
      • coindex (2)
      • collocation (3.3)
      • comparative wordlist (4.3)
      • complements (5.1)
      • complete (9)
      • complex (1.3)
      • complex types (3.1)
      • components (5.5)
      • concatenation (3.2.1)
      • conclusion (2)
      • conditional expression (4.3)
      • conditional frequency distribution (2)
      • conditional (6.3)
      • confusion matrix (3.4)
      • consecutive classification (1.6)
      • consistent (1.2)
      • constituent (2.1)
      • constituent structure (2.1)
      • control (4)
      • control structure (4.3)
      • Cooper storage (4.5)
      • coordinate structure (2.1)
      • copy (4.1.1)
      • coreferential (3.1)
      • corpora (0)
      • Corpus Linguistics (7)
      • cross-validation (3.5)

    • D

      • data intensive (I)
      • debugger (4.6.4)
      • decision nodes (4)
      • decision stump (4)
      • decision tree (4)
      • decoding (3.3.1)
      • defensive programming (4.4.4)
      • dependents (5)
      • determiners (2.6)
      • dev-test (1.2)
      • development set (1.2)
      • dialogue acts (2.2)
      • dictionary (3)
      • dictionary (3.2)
      • directed acyclic graphs (2)
      • discourse (5)
      • discourse referents (5.1)
      • discourse representation structure (5.1)
      • dispersion plot (1.3)
      • divide-and-conquer (4.7)
      • docstring (4.4)
      • doctest block (4.4.6)
      • domain (3.4)
      • DRS conditions (5.1)
      • duck typing (4.3)
      • dynamic programming (4.4)

    • E

      • empiricism (II)
      • encode (1.1)
      • encoding (3.3.1)
      • entails (5.3)
      • equivalent (2)
      • error analysis (1.2)
      • evaluation set (3.1)
      • existential quantifier (3.1)
      • Expected Likelihood Estimation (5.2)
      • export (3.9.2)

    • F

      • F-Measure (3.3)
      • F-Score (3.3)
      • f-structure (5)
      • False negatives (3.3)
      • False positives (3.3)
      • feature extractor (1.1)
      • feature (1.2)
      • feature path (2)
      • feature set (1.1)
      • feature structures (1)
      • features (1.1)
      • fields (4.2.2)
      • filler (3.4)
      • folds (3.5)
      • formal language theory (I)
      • format string (3.9.2)
      • free (3.1)
      • frequency distribution (3.1)
      • function (3.2)

    • G

      • gaps (3.4)
      • gazetteer (5)
      • generalized quantifiers (8)
      • generative grammar (8)
      • generative (6.3)
      • generator expression (4.2.3)
      • gerund (7.1)
      • Glue semantics (7)
      • glyphs (3.3.1)
      • gold standard (4.4)
      • graphs (4.8.2)
      • greedy sequence classification (1.6)

    • H

      • hapaxes (3.1)
      • hash array (3)
      • head features (6)
      • head (5)
      • headword (4)
      • Heldout Estimation (5.2)
      • Hidden Markov Models (1.7)
      • Hole semantics (7)
      • holonyms (5.3)
      • homonyms (4)
      • hyponyms (5.2)

    • I

      • idealism (II)
      • identifiers (2.3)
      • immediate constituents (2.1)
      • immutable (4.2.2)
      • inconsistent (1.2)
      • indented code block (1.4)
      • independence assumption (5.1)
      • index (2.2)
      • inference (2)
      • Information Extraction (1)
      • information gain (4.1)
      • Inline annotation (3.5)
      • interpreter (1.1)
      • IOB tags (2.6)
      • iterative optimization (6)

    • J

      • joint classifier (1.6)
      • joint-feature (6.1)

    • K

      • Kappa (2.2)
      • key (3.2)
      • keyword arguments (4.5.4)
      • Kleene closures (3.4.2)

    • L

      • lambda expressions (4.5.1)
      • latent semantic analysis (4.8.4)
      • leaf nodes (4)
      • left-corner (4.3)
      • left-corner parser (4.3)
      • left-recursive (3.3)
      • lemma (4)
      • letter trie (4.7.1)
      • lexical acquisition (9)
      • lexical categories (0)
      • lexical entry (4)
      • lexical relations (5.3)
      • lexicon (10)
      • LGB rule (4.4.3)
      • library (3.3)
      • licensed (3.4)
      • likelihood ratios (1.1)
      • Linear-Chain Conditional Random Field Models (1.7)
      • list (2.1)
      • local variables (3.2)
      • logical constants (3.1)
      • logical form (2)

    • M

      • machine translation (5.3)
      • mapping (3)
      • maximal projection (3.2)
      • Maximum Entropy (6)
      • Maximum Entropy Markov Models (1.7)
      • Maximum Entropy principle (6.2)
      • meronyms (5.3)
      • methods (3.2)
      • modals (2.6)
      • model checking (3.5)
      • model (1.2)
      • models (7)
      • module (3.3)
      • morpho-syntactic (7.5)
      • morphological analysis (7.5)
      • multiword expression (3.11)
      • mutable (4.2.2)

    • N

      • n-gram tagger (5.3)
      • naive Bayes assumption (5.1)
      • naive Bayes (5)
      • named entity detection (1.1)
      • named entity recognition (5)
      • newlines (3.1.5)
      • NLTK Data Repository (6.3)
      • non-logical constants (3.1)
      • non-standard words (3.6.2)
      • normalized (3.6)
      • noun phrase chunking (2.1)
      • noun phrase (II)
      • NP-chunking (2.1)

    • O

      • objective function (3.8.2)
      • open class (7.4)
      • open formula (3.1)
      • out-of-vocabulary (5.5)
      • overfit (4.1)
      • overfitting (1.2)

    • P

      • package (3.3)
      • parameter (1.4)
      • parameters (5.5)
      • parent (4.2)
      • parser (4)
      • part-of-speech tagging (0)
      • partial information (2.1)
      • parts of speech (0)
      • personal pronouns (2.6)
      • phonology (I)
      • phrasal level (3.2)
      • POS-tagger (1)
      • POS-tagging (0)
      • pre-sort (4.7)
      • Precision (3.3)
      • precision/recall trade-off (5.3)
      • predicates (3.1)
      • prepositional phrase attachment ambiguity (3.1)
      • prepositional phrase (2.1)
      • present participle (7.1)
      • principle of compositionality (I)
      • prior probability (5)
      • probabilistic context free grammar (6.3)
      • productions (1.1)
      • projective (5)
      • proof goal (3.2)
      • Propositional logic (2)
      • propositional symbols (2)
      • prune (4.1)

    • Q

      • question answering (5.3)

    • R

      • rationalism (II)
      • raw string (3.4.2)
      • realism (II)
      • Recall (3.3)
      • recognizing (4.4)
      • record (4.2.2)
      • recursion (4.7.1)
      • recursive (3.3)
      • reduce (4.2)
      • reentrancy (2)
      • refactor (4.4.5)
      • regression testing (4.6.5)
      • relation detection (1.1)
      • relational operators (4.1)
      • replacement field (3.9.2)
      • return value (3.2)
      • root element (4.3)
      • root node (4)
      • runtime error (2.2)

    • S

      • S-Retrieval (4.5)
      • satisfies (3.5)
      • scope (3.7)
      • segmentation (3.8)
      • semantic role labeling (5.2)
      • sequence classifier (1.6)
      • sequence (3.2.6)
      • shift (4.2)
      • shift-reduce parser (4.2)
      • siblings (4.2)
      • signature (3.1)
      • slash categories (3.4)
      • slicing (2.2)
      • smoothing (5.2)
      • stack trace (4.6.4)
      • standoff annotation (2.3)
      • standoff annotation (3.5)
      • start-symbol (3.1)
      • stopwords (4.1)
      • string formatting (3.9.2)
      • string (3.2)
      • strings (2.4)
      • structurally ambiguous (3.1)
      • structure sharing (2)
      • structured data (1)
      • stylistics (1.3)
      • subcategorized (5.1)
      • subsumption (2.1)
      • subtype (5)
      • supervised (1)
      • Swadesh wordlists (4.3)
      • symbolic logic (I)
      • synonyms (5.1)
      • synset (5.1)
      • syntax error (1.1)

    • T

      • T9 (3.4.2)
      • tag (2)
      • tag patterns (2.2)
      • tagged (2.2)
      • tagging (0)
      • tagset (0)
      • terms (3.1)
      • test set (1.1)
      • test set (3.1)
      • text alignment (5.4)
      • textonyms (3.4.2)
      • token (1.4)
      • tokenization (3.1.1)
      • top-down (4.7.3)
      • top-down parsing (4.1)
      • total likelihood (6)
      • train (5.1)
      • training (5.1)
      • training set (1.1)
      • training set (1.2)
      • transitive verbs (5.1)
      • tree (4.2)
      • True negatives (3.3)
      • True positives (3.3)
      • truth-conditions (2)
      • tuple (4.2)
      • Turing Test (5.5)
      • Type I errors (3.3)
      • Type II errors (3.3)
      • type-raising (4.3)
      • Typed feature structures (5)
      • types (3.1)

    • U

      • unary predicate (3.1)
      • unbounded dependency construction (3.4)
      • underspecified (1.2)
      • unification (2.1)
      • unique beginners (5.2)
      • universal quantifier (3.1)
      • unseen (7)
      • unstructured data (1)

    • V

      • valencies (5.1)
      • valid (2)
      • validity (4.1)
      • valuation function (3.4)
      • value (3.2)
      • variable (2.3)
      • verb phrase (2.1)

    • W

      • weights (5.5)
      • well formed formulas (2)
      • well formed (4.1)
      • well-formed substring table (4.4)
      • wildcard (3.4.1)
      • word classes (0)
      • word sense disambiguation (5.1)
      • word type (1.4)
      • WordNet (5)

    • X

      • XML attribute (4.1)
      • XML element (4.1)

    • Z

      • zero projection (3.2)

    • Α

      • α-conversion (4.2)
      • α equivalents (4.2)

    • Β

      • β-reduction (4.2)

    • Λ

      • λ abstraction (4.2)
      • λ operator (4.2)

    About this document…

    UPDATED FOR NLTK 3.0. This is a chapter from Natural Language Processing with Python, by Steven Bird, Ewan Klein and Edward Loper, Copyright © 2014 the authors. It is distributed with the Natural Language Toolkit [http://nltk.org/], Version 3.0, under the terms of the Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License [http://creativecommons.org/licenses/by-nc-nd/3.0/us/].

    This document was built on Wed 1 Jul 2015 12:30:05 AEST