Index

_
- (phrasal) projections (10.4.2)
A
- A* Parser (8.4.2)
- A* parser (8.4.3)
- adjectives (3.5.1)
- adverbs (3.5.1)
- agreement (10.2.1)
- American National Corpus (12.2)
- appropriate (10.6)
- articles (3.5.1)
- artificial intelligence (1.1.2)
- Assignment (11.3.2)
- assigns (1.3.2)
- associative array (5.2.6)
- atomic (10.2.3)
- attribute value matrix (10.2.3)
- auxiliaries (10.4.3)
- auxiliary (10.2.3)
B
- backtracks (7.5.1)
- base (2.3.2)
- beam search (8.4.4)
- best-first search strategy (8.4.4)
- bigram (2.3.2)
- binary predicate (11.3.1)
- BIO Format (6.9)
- body (1.5.2)
- Boolean context (1.6.5)
- boolean (10.2.3)
- bottom-up (5.5.3)
- Bottom-Up Initialization Rule (8.3.3)
- Bottom-Up Initialization Rule (8.3.3)
- bottom-up parsing (7.5.1)
- Bottom-Up Predict Rule (8.3.3)
- Bottom-Up Predict Rule (8.3.3)
- Bottom-Up Strategy (8.3.3)
- British National Corpus (12.2)
- business information analysis (1.1.2)
C
- call-by-value (5.4.2)
- call (1.4.1)
- call structure (5.5.3)
- cartesian product (5.2.5)
- Catalan numbers (8.1)
- characters (1.4)
- chart (8.2.2)
- chart parsing (8.2)
- chart parsing (8.2)
- child (7.3.3)
- CHILDES (12.2)
- chink (6.4.4)
- chink (6.9)
- chinking (6.4.4)
- chunker (6.3)
- chunking (6.1)
- chunks (6.1)
- closed class (3.5.2)
- closed formula (11.3.3)
- coindex (10.3.2)
- common nouns (3.2.2)
- complements (7.4.3)
- complete edge (8.3)
- complete (8.4.4)
- complex (10.2.3)
- compound keys (5.2.6)
- computer science (1.1.2)
- concatenation (1.3.1)
- conditional expression (1.6.1)
- conditional frequency distribution (2.4.6)
- constituency (7.3.2)
- constituents (7.3.2)
- context-free grammar (7.4)
- control structure (1.5.2)
- control structure (1.6.1)
- conversion specifier (1.5.3)
- copy (5.2.1)
- Corpus Linguistics (2.4.2)
- count nouns (3.2.2)
- counters (1.7.2)
D
- data types (1.6.4)
- daughter (7.3.3)
- decorator (5.5.3)
- decrease-and-conquer (5.5)
- delimited (1.3.1)
- dependency grammar (7.4.4)
- derivation (7.4.5)
- determiners (3.5.1)
- diagnosis (6.8)
- dictionary (1.7.1)
- direct recursion (7.4.2)
- directed acyclic graphs (10.3.2)
- divide-and-conquer (5.5)
- docstring (5.4)
- dot (8.3)
- dotted edges (8.3)
- Dublin Core (12.3.6)
- dynamic programming (8.2)
- dynamically typed (5.4.1)
E
- edge queue (8.4.3)
- edge queue (8.4.4)
- equivalent (10.3.2)
- export (5.3.1)
F
- f-structure (10.6)
- feature (10.2.2)
- feature path (10.3.2)
- feature structure (10.2.3)
- fields (5.2.3)
- filler (10.4.4)
- first-in-first-out (5.2.4)
- format string (1.5.3)
- frequency distribution (2.4.1)
- function body (5.4)
- function (5.4)
- Fundamental Rule (8.3.2)
- Fundamental Rule (8.3.2)
G
- gaps (10.4.4)
- General Ontology for Linguistic Description (12.3.5)
- generative grammar (7.6)
- gerund (3.3.1)
- grammar (7.4)
- grammatical productions (7.4.1)
- groups (1.8.1)
- guides (I.5)
H
- head features (10.4.6)
- heads (7.4.3)
- heights (7.3.1)
- homographs (2.3.2)
- human-computer interaction (1.1.2)
- humanities computing (1.1.2)
- hypernym (2.5.2)
- hyponyms (2.5.2)
I
- identifiers (1.3.3)
- immutable (5.2.3)
- immutable (5.2.6)
- import (1.5.4)
- incomplete edge (8.3)
- increment (1.5.2)
- index (1.4.1)
- indexing (1.4.1)
- indirect recursion (7.4.2)
- inflected (2.3.2)
- Information Extraction (6.7)
- interpreter (1.2.1)
- intransitive (3.2.2)
- IOB tags (6.2.2)
- iteration (1.5.2)
K
- Kappa (12.3.7)
- key (1.7.1)
- key-value pairs (1.7.1)
- keywords (1.3.3)
L
- labeling (6.1)
- lambda expressions (5.4.5)
- Lancaster Stemmer (2.3.2)
- last-in-first-out (5.2.4)
- leaves (7.3.1)
- leaves (7.3.1)
- left-corner (7.5.3)
- left-corner parser (7.5.3)
- left recursive (7.4.2)
- lemma (2.3.2)
- lemma (2.3.2)
- Lemmatization (2.3.2)
- lexeme (2.3.2)
- lexical ambiguity (7.3.1)
- lexical categories (3.1)
- lexical productions (7.4.1)
- lexicon (12.2.1)
- licensed (10.4.4)
- licenses (7.4.1)
- linguistic category (10.2.3)
- List comprehensions (2.3.3)
- list (1.5.1)
- logical connectives (11.2)
- long-distance dependency (10.1)
- loop variable (1.5.2)
- lowest-cost-first search strategy (8.4.4)
M
- majority class classifier (3.2.4)
- map (1.7)
- mass nouns (3.2.2)
- matches (1.8)
- maximal projection (10.4.2)
- memoization (5.5.3)
- method (I.5)
- methods (1.5.1)
- modals (3.5.1)
- model (11.1)
- module (1.5.4)
- morpho-syntactic (3.3.1)
- morphological (3.5.2)
- most likely constituents table (8.4.2)
- mutable (5.2.3)
- mutual information (2.4.7)
N
- n-gram tagger (3.5.5)
- Named Entity Recognition (6.1)
- Named Entity Recognition (6.7)
- natural language (I)
- Natural Language Processing (I)
- nested loops (5.2.5)
- newlines (2.2.1)
- non-terminal (7.4.1)
- normalization (2.3.2)
- noun phrase (7.3.2)
O
- open formula (11.3.3)
- open (2.2.1)
- out-of-vocabulary (3.5.7)
P
- parent (7.3.3)
- parse edge (8.3)
- parser (7.5)
- part-of-speech tagging (3.1)
- part-of-speech tags (3.1)
- partial information (10.3.3)
- partial parsing (6.2.1)
- parts of speech (3.1)
- past participle (3.3.1)
- personal pronouns (3.5.1)
- phrasal level (10.4.2)
- phrase structure (7.2)
- polysemous (2.5.1)
- Porter Stemmer (2.3.2)
- POS-tagging (3.1)
- POS tags (3.1)
- pre-sort (5.5)
- pre-terminals (7.4.1)
- precision/recall trade-off (3.5.5)
- predicates (11.3.1)
- prepositional phrase attachment ambiguity (7.3.1)
- prepositional phrase attachment ambiguity (7.4.1)
- Prepositional Phrase Attachment Corpus (7.3.1)
- present participle (3.3.1)
- Principle of Compositionality (11.1)
- probabilistic context free grammar (8.4.1)
- productions (7.4)
- proper nouns (3.2.2)
- propositional variables (11.2)
Q
- queue (5.2.4)
R
- raw string (1.8)
- recognizing (8.2.2)
- record (12.2.1)
- recursion (7.4)
- recursion (7.4.2)
- recursive (7.4.2)
- reduce (7.5.2)
- reduce-reduce conflict (7.5.2)
- reentrancy (10.3.2)
- refactor (5.4.3)
- regular expression (1.8)
- regular expression operator (1.8)
- Relation Extraction (6.7)
- relational operators (1.6.2)
- representation (1.3.3)
- root (7.3.1)
- rules (8.3.1)
S
- satisfies (11.3.2)
- Scanner Rule (8.3.5)
- scope (11.3.4)
- segmentation (6.1)
- self-loop edge (8.3)
- semantic (3.5.2)
- semi-structured data (6.7)
- sentence token (2.2)
- sentence type (2.2)
- sequence (1.5.5)
- set (1.7.3)
- shift (7.5.2)
- shift-reduce conflict (7.5.2)
- shift-reduce parser (7.5.2)
- Shoebox (12.2)
- sisters (7.3.3)
- slash categories (10.4.4)
- slice (1.4.2)
- sliding window (5.2.5)
- stack (5.2.4)
- standoff annotation (12.2.3)
- start-symbol (7.4.1)
- stem (2.3.2)
- strategy (8.3.1)
- string formatting expressions (1.5.3)
- string (1.3.1)
- structurally ambiguous (7.4.1)
- structure sharing (10.3.2)
- structured data (6.7)
- subcategories (7.4.3)
- Subject-Auxiliary Inversion (7.3.2)
- subscripting (1.4.1)
- substrings (1.4)
- subsumes (10.3.3)
- subsumption (10.3.3)
- subtype (10.6)
- suffix (2.3.2)
- synonyms (2.5.1)
- synsets (2.5)
- syntactic (3.5.2)
- syntax error (1.2.1)
T
- tag (10.3.2)
- tag pattern (6.3.1)
- tag set (3.1)
- tagged (3.1)
- tagging (3.1)
- terminals (7.4.1)
- terms (11.3.1)
- text (12.2.1)
- the principle of compositionality (11.4.1)
- token (2.2)
- tokenization (2.2)
- Toolbox (12.2)
- Top-Down Expand Rule (8.3.4)
- Top-Down Expand Rule (8.3.4)
- top-down (5.5.3)
- Top-Down Initialization Rule (8.3.4)
- Top-Down Initialization Rule (8.3.4)
- Top-Down Match Rule (8.3.4)
- Top-Down Match Rule (8.3.4)
- top-down parsing (7.5.1)
- Top-Down Strategy (8.3.4)
- training (3.5.3)
- transform-and-conquer (5.5)
- transitive (3.2.2)
- transitive verbs (7.4.3)
- tree diagram (7.3.1)
- tuple (3.2.1)
- tuples (1.8.1)
- type (2.2)
- type (2.2)
- type raising (11.4.3)
- Typed feature structures (10.6)
U
- unary predicate (11.3.1)
- unbounded dependency construction (10.4.4)
- underspecified (10.2.2)
- unification (10.3.3)
- unify (10.2.2)
- unigram chunker (6.5.1)
- unique beginners (2.5.2)
- unstructured data (6.7)
V
- valency (7.4.3)
- value (1.3.2)
- value (1.7.1)
- variable (1.3.2)
W
- Web software development (1.1.2)
- well-formed substring table (8.2.1)
- word classes (3.1)
- WordNet (2.5)
Z
- zero projection (10.4.2)

About this document...

This chapter is a draft from Natural Language Processing [http://nltk.org/book.html], by Steven Bird, Ewan Klein and Edward Loper, Copyright © 2008 the authors. It is distributed with the Natural Language Toolkit [http://nltk.org/], Version 0.9.5, 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 is