國立虎尾科技大學 |

Bayesian analysis in natural language processing /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Bayesian analysis in natural language processing // Shay Cohen.
作者:	Cohen, Shay,
其他作者:	Hirst, Graeme.
面頁冊數:	1 PDF (xxxi, 311 pages) :illustrations. :
附註:	Part of: Synthesis digital library of engineering and computer science.
標題:	Natural language processing (Computer science) -
電子資源:	https://ieeexplore.ieee.org/servlet/opac?bknumber=8686829
電子資源:	https://doi.org/10.2200/S00905ED2V01Y201903HLT041
ISBN:	9781681735276

Bayesian analysis in natural language processing /
Cohen, Shay,

Bayesian analysis in natural language processing /Shay Cohen. - Second edition. - 1 PDF (xxxi, 311 pages) :illustrations. - Synthesis lectures on human language technologies,#411947-4059 ;. - Synthesis lectures on human language technologies ;#18. .

Part of: Synthesis digital library of engineering and computer science.

Includes bibliographical references (pages 275-303) and index.

1. Preliminaries -- 1.1. Probability Measures -- 1.2. Random Variables -- 1.3. Conditional Distributions -- 1.4. Expectations of Random Variables -- 1.5. Models -- 1.6. Learning from Data Scenarios -- 1.7. Bayesian and Frequentist Philosophy (Tip of the Iceberg) -- 1.8. Summary -- 1.9. Exercises

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

Natural language processing (NLP) went through a profound transformation in the mid-1980s when it shifted to make heavy use of corpora and data-driven techniques to analyze language. Since then, the use of statistical techniques in NLP has evolved in several ways. One such example of evolution took place in the late 1990s or early 2000s, when full-fledged Bayesian machinery was introduced to NLP. This Bayesian approach to NLP has come to accommodate various shortcomings in the frequentist approach and to enrich it, especially in the unsupervised setting, where statistical learning is done without target prediction examples. In this book, we cover the methods and algorithms that are needed to fluently read Bayesian learning papers in NLP and to do research in the area. These methods and algorithms are partially borrowed from both machine learning and statistics and are partially developed "in-house" in NLP. We cover inference techniques such as Markov chain Monte Carlo sampling and variational inference, Bayesian estimation, and nonparametric modeling. In response to rapid changes in the field, this second edition of the book includes a new chapter on representation learning and neural networks in the Bayesian context. We also cover fundamental concepts in Bayesian statistics such as prior distributions, conjugacy, and generative modeling. Finally, we review some of the fundamental modeling techniques in NLP, such as grammar modeling, neural networks and representation learning, and their use with Bayesian analysis.

Mode of access: World Wide Web.

ISBN: 9781681735276

Standard No.: 10.2200/S00905ED2V01Y201903HLT041doiSubjects--Topical Terms:

641811
Natural language processing (Computer science)
Subjects--Index Terms:

natural language processingIndex Terms--Genre/Form:

554714
Electronic books.

LC Class. No.: QA76.9.N38 / C643 2019eb

Dewey Class. No.: 006.35

Bayesian analysis in natural language processing /
LDR:07117nam 2200709 i 4500 001 959756
003 IEEE
005 20190503190106.0
006 m eo d
007 cr bn |||m|||a
008 201209s2019 caua fob 001 0 eng d
020 $a 9781681735276 $q electronic
020 $z 9781681735283 $q hardcover
020 $z 9781681735269 $q paperback
024 7 $a 10.2200/S00905ED2V01Y201903HLT041 $2 doi
035 $a (CaBNVSL)thg00978841
035 $a (OCoLC)1097979255
035 $a 8686829
040 $a CaBNVSL $b eng $e rda $c CaBNVSL $d CaBNVSL
050 4 $a QA76.9.N38 $b C643 2019eb
082 0 4 $a 006.35 $2 23
100 1 $a Cohen, Shay, $e author. $3 1253082
245 1 0 $a Bayesian analysis in natural language processing / $c Shay Cohen.
250 $a Second edition.
264 1 $a [San Rafael, California] : $b Morgan & Claypool, $c [2019]
300 $a 1 PDF (xxxi, 311 pages) : $b illustrations.
336 $a text $2 rdacontent
337 $a electronic $2 isbdmedia
338 $a online resource $2 rdacarrier
490 1 $a Synthesis lectures on human language technologies, $x 1947-4059 ; $v #41
500 $a Part of: Synthesis digital library of engineering and computer science.
504 $a Includes bibliographical references (pages 275-303) and index.
505 0 $a 1. Preliminaries -- 1.1. Probability Measures -- 1.2. Random Variables -- 1.3. Conditional Distributions -- 1.4. Expectations of Random Variables -- 1.5. Models -- 1.6. Learning from Data Scenarios -- 1.7. Bayesian and Frequentist Philosophy (Tip of the Iceberg) -- 1.8. Summary -- 1.9. Exercises
505 8 $a 2. Introduction -- 2.1. Overview : Where Bayesian Statistics and NLP Meet -- 2.2. First Example : The Latent Dirichlet Allocation Model -- 2.3. Second Example : Bayesian Text Regression -- 2.4. Conclusion and Summary -- 2.5. Exercises
505 8 $a 3. Priors -- 3.1. Conjugate Priors -- 3.2. Priors Over Multinomial and Categorical Distributions -- 3.3. Non-Informative Priors -- 3.4. Conjugacy and Exponential Models -- 3.5. Multiple Parameter Draws in Models -- 3.6. Structural Priors -- 3.7. Conclusion and Summary -- 3.8. Exercises
505 8 $a 4. Bayesian Estimation -- 4.1. Learning with Latent Variables : Two Views -- 4.2. Bayesian point estimation -- 4.3. Empirical Bayes -- 4.4. Asymptotic behavior of the posterior -- 4.5. Summary -- 4.6. Exercises
505 8 $a 5. Sampling methods -- 5.1. MCMC algorithms : overview -- 5.2. NLP model structure for MCMC inference -- 5.3. Gibbs sampling -- 5.4. The Metropolis-Hastings algorithm -- 5.5. Slice sampling -- 5.6. Simulated annealing -- 5.7. Convergence of MCMC algorithms -- 5.8. Markov chain : basic theory -- 5.9. Sampling algorithms not in the MCMC realm -- 5.10. Monte Carlo integration -- 5.11. Discussion -- 5.12. Conclusion and summary -- 5.13. Exercises
505 8 $a 6. Variational inference -- 6.1. Variational bound on marginal log-likelihood -- 6.2. Mean-field approximation -- 6.3. Mean-field variational inference algorithm -- 6.4. Empirical Bayes with variational inference -- 6.5. Discussion -- 6.6. Summary -- 6.7. Exercises
505 8 $a 7. Nonparametric priors -- 7.1. The dirichlet process : three views -- 7.2. Dirichlet process mixtures -- 7.3. The hierarchical Dirichlet process -- 7.4. The Pitman-Yor process -- 7.5. Discussion -- 7.6. Summary -- 7.7. Exercises
505 8 $a 8. Bayesian grammar models -- 8.1. Bayesian hidden Markov models -- 8.2. Probabilistic context-free grammars -- 8.3. Bayesian probabilistic context-free grammars -- 8.4. Adaptor grammars -- 8.5. Hierarchical Dirichlet process PCFGS (HDP-PCFGS) -- 8.6. Dependency grammars -- 8.7. Synchronous grammars -- 8.8. Multilingual learning -- 8.9. Further reading -- 8.10. Summary -- 8.11. Exercises
505 8 $a 9. Representation learning and neural networks -- 9.1. Neural networks and representation learning : why now? -- 9.2. Word embeddings -- 9.3. Neural networks -- 9.4. Modern use of neural networks in NLP -- 9.5. Tuning neural networks -- 9.6. Generative modeling with neural networks -- 9.7. Conclusion -- 9.8. Exercises
505 8 $a A. Basic concepts -- A.1. Basic concepts in information theory -- A.2. Other basic concepts -- A.3. Basic concepts in optimization -- B. Distribution catalog -- B.1. The multinomial distribution -- B.2. The Dirichlet distribution -- B.3. The Poisson distribution -- B.4. The gamma distribution -- B.5. The multivariate normal distribution -- B.6. The Laplace distribution -- B.7. The logistic normal distribution -- B.8. The inverse Wishart distribution -- B.9. The Gumbel distribution.
506 $a Abstract freely available; full-text restricted to subscribers or individual document purchasers.
510 0 $a Compendex
510 0 $a INSPEC
510 0 $a Google scholar
510 0 $a Google book search
520 3 $a Natural language processing (NLP) went through a profound transformation in the mid-1980s when it shifted to make heavy use of corpora and data-driven techniques to analyze language. Since then, the use of statistical techniques in NLP has evolved in several ways. One such example of evolution took place in the late 1990s or early 2000s, when full-fledged Bayesian machinery was introduced to NLP. This Bayesian approach to NLP has come to accommodate various shortcomings in the frequentist approach and to enrich it, especially in the unsupervised setting, where statistical learning is done without target prediction examples. In this book, we cover the methods and algorithms that are needed to fluently read Bayesian learning papers in NLP and to do research in the area. These methods and algorithms are partially borrowed from both machine learning and statistics and are partially developed "in-house" in NLP. We cover inference techniques such as Markov chain Monte Carlo sampling and variational inference, Bayesian estimation, and nonparametric modeling. In response to rapid changes in the field, this second edition of the book includes a new chapter on representation learning and neural networks in the Bayesian context. We also cover fundamental concepts in Bayesian statistics such as prior distributions, conjugacy, and generative modeling. Finally, we review some of the fundamental modeling techniques in NLP, such as grammar modeling, neural networks and representation learning, and their use with Bayesian analysis.
530 $a Also available in print.
538 $a Mode of access: World Wide Web.
538 $a System requirements: Adobe Acrobat Reader.
588 $a Title from PDF title page (viewed on May 3, 2019).
650 0 $a Natural language processing (Computer science) $3 641811
650 0 $a Bayesian statistical decision theory. $3 527671
653 $a natural language processing
653 $a computational linguistics
653 $a Bayesian statistics
653 $a Bayesian NLP
653 $a statistical learning
653 $a inference in NLP
653 $a grammar modeling in NLP
653 $a neural networks
653 $a representation learning
655 0 $a Electronic books. $2 local $3 554714
700 1 $a Hirst, Graeme. $3 1253083
776 0 8 $i Print version: $z 9781681735283 $z 9781681735269
830 0 $a Synthesis lectures on human language technologies ; $v #18. $3 931364
830 0 $a Synthesis digital library of engineering and computer science. $3 598254
856 4 2 $3 Abstract with links to resource $u https://ieeexplore.ieee.org/servlet/opac?bknumber=8686829
856 4 0 $3 Abstract with links to full text $u https://doi.org/10.2200/S00905ED2V01Y201903HLT041