Главная    Ex Libris    Книги    Журналы    Статьи    Серии    Каталог    Wanted    Загрузка    ХудЛит    Справка    Поиск по индексам    Поиск    Форум   
blank
Авторизация

       
blank
Поиск по указателям

blank
blank
blank
Красота
blank
Charniak E. — Statistical Language Learning
Charniak E. — Statistical Language Learning

Читать книгу
бесплатно

Скачать книгу с нашего сайта нельзя

Обсудите книгу на научном форуме



Нашли опечатку?
Выделите ее мышкой и нажмите Ctrl+Enter


Название: Statistical Language Learning

Автор: Charniak E.

Аннотация:

Eugene Charniak breaks new ground in artificial intelligence research by presenting statistical language processing from an artificial intelligence point of view in a text for researchers and scientists with a traditional computer science background.

New, exacting empirical methods are needed to break the deadlock in such areas of artificial intelligence as robotics, knowledge representation, machine learning, machine translation, and natural language processing (NLP). It is time, Charniak observes, to switch paradigms. This text introduces statistical language processing techniques — word tagging, parsing with probabilistic context free grammars, grammar induction, syntactic disambiguation, semantic word classes, word-sense disambiguation — along with the underlying mathematics and chapter exercises.

Charniak points out that as a method of attacking NLP problems, the statistical approach has several advantages. It is grounded in real text and therefore promises to produce usable results, and it offers an obvious way to approach learning: "one simply gathers statistics."


Язык: en

Рубрика: Технология/

Статус предметного указателя: Готов указатель с номерами страниц

ed2k: ed2k stats

Год издания: 1994

Количество страниц: 162

Добавлена в каталог: 07.12.2005

Операции: Положить на полку | Скопировать ссылку для форума | Скопировать ID
blank
Предметный указатель
$\overline{X}$ theory      8 106 111
Accepting states, of Markov processes      32
Acceptors      32
adj      3
Adjective-noun attachment      20
Adjective-noun modification      129
Adv      3
Aligning corpora      148
Ambiguity, in tagging      49
Ambiguous grammars      6
Antonyms      144
artificial intelligence      1
Attachment decisions      119
AutoClass      155
AUX      3
Average mutual information      138 46
Backward probability      58
Backward probability, algorithm for      60
Backward probability, relation to PCFGs      89
Basili, R.      124
Baum — Welch algorithm      60
Bayes’ Law      22
Bigrams      40
Binary Tanimoto measure      142
bits      27
Boggess, L.      50
Bracketed corpora      108—111 117
Bracketing      109
Breadth-first numbering      131
Briscoe, T.      111
Brown Corpus      48
Brown corpus, number of word-types in      120
Brown corpus, size of      36
Brown corpus, tagged version      49
Brown, P.      136 143 148
Buckshot      155
Canadian parliament      148
Carroll, G.      105
Centroid      141 159
CFGs      4
Charniak, E.      51 105
Chart      9
Chart parsing      9—16 20 75
Chart parsing for PCFGs      91
Chart parsing, algorithm      10 19
Chart parsing, most likely parse in      101
Chomsky-normal form      8
Chomsky-normal form for PCFG proofs      89 94
Chomsky-normal form, in grammar induction      108 111
Church, K.W.      50 52
Clustering      135—136
CNF      89
Co-reference      19
Code trees      28 30
Coding theory      27
Cognitive psychology      81
Compositional semantics      17
compress      29
Computational linguistics      1
Conditional entropy      138 145
Conditional probability      22
CONJ      3
Context as direct object      139
Context as next word      136
Context as syntactically related material      142
Context as word window      139
Context in speech recognition      1
Context-free grammars      4—9
Context-free languages      75
Context-free parsers      9
Corpus      24
Cosine, as a distance metric      154
Critical points      104
Critical points in HMM training      65
Critical points in PCFG training      98
Cross entropy      33
Cross entropy as a model evaluator      34—38
Cross entropy of a language      34
Cross validation      36
Cycles in grammars      16
Database classification      1
Dependency grammars      106 117
DeRose, S.J.      50
DET      3
Distance metrics      135
Domains of discourse      125
Dominance      76
E-transitions      43
Edges in chart parsing      92
Edges of a chart      10
Edges of an HMM      43
Edges, adding and removing      12
entropy      27—31 29
Entropy of a language      31
Entropy, conditional      145
Entropy, pet word      30
Ergodic      34 36
Euclidean distance      135
Euclidean distance in sense disambiguation      154
Euclidean distance in word clustering      136 146
features      3
file compression      29
Final state, of a finite automata      32
Finite-state automaton      32
First-order predicate calculus      17
Fisher, D.      127
Forward probability      57
Forward probability, algorithm for      57
Forward probability, relation to PCFGs      89
Forward-backward algorithm      60
Fpunc      3
Francis, S.      36
French translation      148
Gale, W.A.      144 148
gaps      127
Generators      32
Grammar      4
Grammar induction      80 103—116
Greedy algorithm      138
Grefenstette, G.      142 143 144
Hansards      148
Head constituent      84 131
Hidden Markov models      39 41—45 43 53—70 87—88
Hindle, D.      121 124 126
HMMs      39
Initial state, of an HMM      43
Inside probability      89 101
Inside probability, algorithm for      93
Inside-outside algorithm, in grammar induction      104
Jackendoff, R.      8
Jelinek, F.      49 52
Key list      9
Knowledge representation      139
Kucera, H.      36
Language models, using PCFGs      83 130
Language models, using trigrams      39
Lexical items      2
Lexical rules      83
Lexicon      2
Local maxima in grammar induction      104
Local maxima in HMM training      68
Local maxima in PCFG training      98
Logical object      128
Logical subject      128
Long-distance dependencies      8
Machine Translation      148
Markov assumptions      44
Markov assumptions for PCFG language models      131
Markov assumptions for PCFG parses      78
Markov assumptions for tagging      47
Markov chains      32
Markov chains for ttigram models      40 42
Markov chains, order of      40
Markov chains, training for      60
Maximum entropy      159
modal      3
Morphology      2—4
Multiplying out features      8
Mutual information      136 146 157
Mutual information, average      138
N-gram models      39
Negative training examples      80 103 106
NLU      1
Non-terminals as chart entries      9
Non-terminals for PCFGs      75
Non-terminals in $\overline{X}$ theory      8
Non-terminals in grammar induction      104
Non-terminals of CFGs      5
Non-terminals, multiplying out      8
Non-terminals, unexpandable      20
Noun      3
Noun-noun attachment      20
Noun-noun attachment, mistakes in      113
Noun-noun modification      129
Noun-phrase reference      19
NP      5
Null hypothesis      122
Number feature      3
Oracles      81
Order, of Markov chains      40
Outside probability      101 90 94
Outside probability, algorithm for      96
Overfitting data, of word senses      158
Overfitting parameters      67
Parallel French-English corpora      148
Parse, most probable      79 100 111
Parser, partial      121
Parses, number of possible      16
Part-of-speech tagging      45—51 52
Part-of-speech tagging, performance      51
Partial bracketing      109
Partial parsers      139 142
Parts of speech      3 83
Passive sentences      128
Paths through an HMM      45 52 53—56
PCFG      75
Per-word cross entropy      33
Per-word entropy      30
Pereira, F.      108 139 158
Person feature      3
Plural nouns      2
pos      3
Positive training examples      80 106
Pragmatics      2
Prep      3
Prepositional-phrase attachment      16 19 79 113 119—126
Pro      3
Probabilistic context-free grammars      20 75 75—99 119
Probability of a PCFG parse      76
Probability of a PCFG rule      75
Probability of an HMM transition      44
Probability of HMM output      57
Probability of most likely HMM path      53
Probability theory      21—24
PROP      3
Pseudo-words      39 51
Random variable      21
Reference      19
Regular grammars      87
Regular languages      87
Relative clauses      127
Relative entropy      141
Relative pronouns      127
Relative-clause attachment      126—129
Resnik, P.      156
Restrictive relative clauses      127
Rewrite rules for dependency grammars      106 117
Rewrite rules for PCFGs      75
Rewrite rules in Chomsky-noimal form      8
Rewrite rules of CFGs      5
Riloff, E.      127
Roget classes, as a gold standard      143
Roget’s Thesaurus      143 150
Root forms      2
Rooth, M.      121 124 126
Rule-length restrictions      104
S      5
S-maj      5
Saddle points      65
Schabes, Y.      108
Schuetze, H.      151 158
SEC corpus      113
Selectional restrictions      18
Selectional restrictions, discovery of      155—159
Semantic information, use during parsing      123—134
Semantic tags      124 129
Semantics      2
senses      16
Sentence bracketing      109
Singular nouns      2
Slash categories      9
Smoothing the trigram model      40 51 52 139
Source language, in machine translation      148
Sparse data      40
Sparse data and semantic tags      129
Sparse data for selectional restrictions      156
Sparse data for sense disambiguation      150
Sparse data for tagging      48
Sparse data for trigram models      40
Sparse data in PCFG language models      133
Sparse data in pp attachment      120 121
Speech recognition      1 25 26 30
Start state, of a finite automata      32
Starting symbol, for PCFGs      75
States, of an HMM      43
Statistical models      24—26
Subject-verb agreement      3 8
suffixes      2
Syntactic ambiguity      79
Syntactic disambiguation      119—134
Syntactic parsers      75
Syntactic structure      4
Syntax      2
T-scores      122 122 129
Tags      46
Tanimoto measure      142
Target language, in machine translation      148
Terminal symbols      5 75
Terminal symbols as chart entries      9
Terminal symbols in dependency grammars      106
Time ticks, of an HMM      44
Tishby, N.      139 158
Tokens, word      37
Training HMMs      60—70 73
Training HMMs for trigram smoothing      41
Training HMMs, algorithm for      63
Training PCFGs      96—99 109
Training PCFGs for grammar induction      101
Training sequences for HMMs      66
Training sequences for PCFGs      98
Transitions, of an HMM      43
Trigram models      39
Trigram models of English      39—43
Trigram models of English, cross entropy      139
Trigram models of English, vs PCFGs      83
Types, word      37
Ungrammatical sentences      82
Unigrams      40
Universe of all outcomes      22
UNIX      29
1 2
blank
Реклама
blank
blank
HR
@Mail.ru
       © Электронная библиотека попечительского совета мехмата МГУ, 2004-2018
Электронная библиотека мехмата МГУ | Valid HTML 4.01! | Valid CSS! О проекте