Introduction to natural language processing:
"The book provides a technical perspective on the most contemporary data-driven approaches, focusing on techniques from supervised and unsupervised machine learning. It also includes background in the salient linguistic issues, as well as computational representations and algorithms. The first...
Gespeichert in:
1. Verfasser: | |
---|---|
Format: | Buch |
Sprache: | English |
Veröffentlicht: |
Cambridge, MA
The MIT Press
[2019]
|
Schriftenreihe: | Adaptive computation and machine learning series
|
Schlagworte: | |
Online-Zugang: | Inhaltsverzeichnis Klappentext |
Zusammenfassung: | "The book provides a technical perspective on the most contemporary data-driven approaches, focusing on techniques from supervised and unsupervised machine learning. It also includes background in the salient linguistic issues, as well as computational representations and algorithms. The first section of the book explores what can be with individual words. The second section concerns structured representations such as sequences, trees, and graphs. The third section highlights different approaches to the representation and analysis of linguistic meaning. The final section describes three of the most transformative applications of natural language processing: information extraction, machine translation, and text generation. The book describes the technical foundations of the field, including the most relevant machine learning techniques, algorithms, and linguistic representations. From these foundations, it extends to contemporary research in areas such as deep learning. Each chapter contains exercises that include paper-and-pencil analysis of the computational algorithms and linguistic issues, as well as software implementations"-- |
Beschreibung: | xiv, 519 Seiten Illustrationen 24 cm |
ISBN: | 9780262042840 0262042843 |
Internformat
MARC
LEADER | 00000nam a22000008c 4500 | ||
---|---|---|---|
001 | BV046196356 | ||
003 | DE-604 | ||
005 | 20240206 | ||
007 | t | ||
008 | 191014s2019 a||| |||| 00||| eng d | ||
020 | |a 9780262042840 |9 978-0-262-04284-0 | ||
020 | |a 0262042843 |9 0262042843 | ||
035 | |a (OCoLC)1128846302 | ||
035 | |a (DE-599)BVBBV046196356 | ||
040 | |a DE-604 |b ger |e rda | ||
041 | 0 | |a eng | |
049 | |a DE-83 |a DE-20 |a DE-355 |a DE-91G |a DE-573 |a DE-526 |a DE-B768 |a DE-29T |a DE-739 | ||
084 | |a ES 945 |0 (DE-625)27935: |2 rvk | ||
084 | |a ST 306 |0 (DE-625)143654: |2 rvk | ||
084 | |a DAT 710 |2 stub | ||
100 | 1 | |a Eisenstein, Jacob |e Verfasser |0 (DE-588)1199860433 |4 aut | |
245 | 1 | 0 | |a Introduction to natural language processing |c Jacob Eisenstein |
264 | 1 | |a Cambridge, MA |b The MIT Press |c [2019] | |
264 | 4 | |c © 2019 | |
300 | |a xiv, 519 Seiten |b Illustrationen |c 24 cm | ||
336 | |b txt |2 rdacontent | ||
337 | |b n |2 rdamedia | ||
338 | |b nc |2 rdacarrier | ||
490 | 0 | |a Adaptive computation and machine learning series | |
520 | 3 | |a "The book provides a technical perspective on the most contemporary data-driven approaches, focusing on techniques from supervised and unsupervised machine learning. It also includes background in the salient linguistic issues, as well as computational representations and algorithms. The first section of the book explores what can be with individual words. The second section concerns structured representations such as sequences, trees, and graphs. The third section highlights different approaches to the representation and analysis of linguistic meaning. The final section describes three of the most transformative applications of natural language processing: information extraction, machine translation, and text generation. The book describes the technical foundations of the field, including the most relevant machine learning techniques, algorithms, and linguistic representations. From these foundations, it extends to contemporary research in areas such as deep learning. Each chapter contains exercises that include paper-and-pencil analysis of the computational algorithms and linguistic issues, as well as software implementations"-- | |
650 | 0 | 7 | |a Informatik |0 (DE-588)4026894-9 |2 gnd |9 rswk-swf |
650 | 0 | 7 | |a Sprachverarbeitung |0 (DE-588)4116579-2 |2 gnd |9 rswk-swf |
653 | 0 | |a Natural language processing (Computer science) | |
653 | 0 | |a Natural language processing (Computer science) | |
689 | 0 | 0 | |a Sprachverarbeitung |0 (DE-588)4116579-2 |D s |
689 | 0 | 1 | |a Informatik |0 (DE-588)4026894-9 |D s |
689 | 0 | |5 DE-604 | |
856 | 4 | 2 | |m Digitalisierung UB Regensburg - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=031575612&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
856 | 4 | 2 | |m Digitalisierung UB Regensburg - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=031575612&sequence=000003&line_number=0002&func_code=DB_RECORDS&service_type=MEDIA |3 Klappentext |
999 | |a oai:aleph.bib-bvb.de:BVB01-031575612 |
Datensatz im Suchindex
_version_ | 1804180574902943744 |
---|---|
adam_text | Contents Preface ix Notation xiii 1 Introduction 1.1 1.2 1 2 1 Natural Language Processing and Its Neighbors Three Themes in Natural Language Processing LEARNING 11 Linear Text Classification 13 2.1 The Bag of Words 13 2.2 Naive Bayes 17 2.3 Discriminative Learning 24 2.4 Loss Functions and Large-Margin Classification 2.5 Logistic Regression 34 2.6 Optimization 37 2.7 *Additional Topics in Classification 40 2.8 Summary of Learning Algorithms 42 3 Nonlinear Classification 3.1 3.2 3.3 3.4 4 47 Feedforward Neural Networks 48 Designing Neural Networks 50 Learning Neural Networks 53 Convolutional Neural Networks 61 Linguistic Applications of Classification 4.1 4.2 4.3 4.4 4.5 1 5 Sentiment and Opinion Analysis 67 Word Sense Disambiguation 71 Design Decisions for Text Classification Evaluating Classifiers 78 Building Datasets 85 67 74 28
Contents vi 5 Learning without Supervision 5.1 5.2 5.3 5.4 5.5 II 6 91 Unsupervised Learning 91 Applications of Expectation-Maximization 99 Semi-Supervised Learning 102 Domain Adaptation 105 * Other Approaches to Learning with Latent Variables SEQUENCES AND TREES Language Models 117 119 6.1 V-Gram Language Models 120 6.2 Smoothing and Discounting 122 6.3 Recurrent Neural Network Language Models 6.4 Evaluating Language Models 132 6.5 Out-of-Vocabulary Words 134 7 Sequence Labeling 7.1 7.2 7.3 7.4 7.5 7.6 7.7 8 9 183 Regular Languages 184 Context-Free Languages 198 *Mildly Context-Sensitive Languages Context-Free Parsing 10.1 10.2 10.3 10.4 10.5 10.6 167 Part-of-Speech Tagging 167 Morphosyntactic Attributes 173 Named Entity Recognition 175 Tokenization 176 Code Switching 177 Dialogue Acts 178 Formal Language Theory 9.1 9.2 9.3 10 137 Sequence Labeling as Classification 137. Sequence Labeling as Structure Prediction 139 The Viterbi Algorithm 140 Hidden Markov Models 145 Discriminative Sequence Labeling with Features 149 Neural Sequence Labeling 158 *Unsupervised Sequence Labeling 161 Applications of Sequence Labeling 8.1 8.2 8.3 8.4 8.5 8.6 127 209 215 Deterministic Bottom-Up Parsing 216 Ambiguity 219 Weighted Context-Free Grammars 222 Learning Weighted Context-Free Grammars Grammar Refinement 231 Beyond Context-Free Parsing 238 227 109
Contents 11 VII Dependency Parsing 11.1 11.2 11.3 11.4 III MEANING 12 Logical Semantics 12.1 12.2 12.3 12.4 13 243 Dependency Grammar 243 Graph-Based Dependency Parsing 248 Transition-Based Dependency Parsing 253 Applications 261 267 269 Meaning and Denotation 270 Logical Representations of Meaning 270 Semantic Parsing and the Lambda Calculus Learning Semantic Parsers 280 Predicate-Argument Semantics 289 13.1 Semantic Roles 291 13.2 Semantic Role Labeling 295 13.3 Abstract Meaning Representation 14 15 309 The Distributional Hypothesis 309 Design Decisions for Word Representations 311 Latent Semantic Analysis 313 Brown Clusters 315 Neural Word Embeddings 317 Evaluating Word Embeddings 322 Distributed Representations beyond Distributional Statistics Distributed Representations of Multiword Units 327 Reference Resolution 15.1 15.2 15.3 15.4 16 302 Distributional and Distributed Semantics 14.1 14.2 14.3 14.4 14.5 14.6 14.7 14.8 274 333 Forms of Referring Expressions 334 Algorithms for Coreference Resolution 339 Representations for Coreference Resolution 348 Evaluating Coreference Resolution 353 Discourse 357 16.1 Segments 357 16.2 Entities and Reference 16.3 Relations 362 IV APPLICATIONS 377 17 Information Extraction 17.1 Entities 381 17.2 Relations 387 379 359 324
viii Contents 17.3 Events 395 17.4 Hedges, Denials, and Hypothetical 397 17.5 Question Answering and Machine Reading 18 Machine Translation 18.1 18.2 18.3 18.4 18.5 19 405 Machine Translation as a Task 405 Statistical Machine Translation 410 N eural Machine Translation 415 Decoding 423 Training toward the Evaluation Metric Text Generation 424 431 19.1 Data-to-Text Generation 19.2 Text-to-Text Generation 19.3 Dialogue 440 Appendix A: Probability A. 1 A.2 A.3 A.4 A.5 A.6 399 431 437 447 Probabilities of Event Combinations 447 Conditional Probability and Bayes’ Rule 449 Independence 451 Random Variables 451 Expectations 452 Modeling and Estimation 453 Appendix B: Numerical Optimization 455 B.l Gradient Descent 456 B.2 Constrained Optimization 456 B.3 Example: Passive-Aggressive Online Learning Bibliography Index 509 459 457
INTRODUCTION TO NATURAL LANGUAGE PROCESSING JACOB EISENSTEIN This textbook provides a technical perspective on natural language processing—methods for building computer software that understands, generates, and manipulates human language. It emphasizes contemporary data-driven approaches, focusing on techniques from supervised and unsupervised machine learning. The first section estab lishes a foundation in machine learning by building a set of tools that will be used throughout the book and applying them to word-based textual analysis. The second section introduces structured representations of language, includ ing sequences, trees, and graphs. The third section explores different approaches to the representation and analysis of linguistic meaning, ranging from formal logic to neural word embeddings. The final section offers chapter-length treatments of three transformative applications of natural language processing: information extraction, machine translation, and text generation. End-of-chapter exercises include both paper-and-pencil analysis and software implementation. The text synthesizes and distills a broad and diverse research literature, linking contemporary machine learning techniques with the field’s linguistic and computational foundations. It is suitable for use in advanced undergradu ate and graduate-level courses and as a reference for soft ware engineers and data scientists. Readers should have a background in computer programming and college-level mathematics. After mastering the material presented, stu dents will have the technical skill to build
and analyze novel natural language processing systems and to understand the latest research in the field. JACOB EISENSTEIN works at Google as a research scientist. He was previously on the faculty in the School of Interactive Computing at Georgia Institute of Technology. Adaptive Computation and Machine Learning series “Natural language processing is a critically important and rapidly developing area of computer science. Any modern practitioner needs a unified understanding of both machine learning algorithms and linguistic fundamen tals. Jacob Eisenstein is an essential guide through the core technical methodologies of the field and their application in challenging real-world problems. His wonderful textbook is a much-needed resource for any student or researcher interested in mastering contem porary data-driven NLP and gaining a strong foundation for following, and contributing to, future advances. —ALEXANDER RUSH, Associate Professor, Cornell University “This book is a must-read for anyone studying natural language processing. It presents a unified view of the entire field, ranging from linguistic foundations to modern deep learning algorithms, that is both technically rigorous and also easily accessible.” —LUKE ZETTLEMOYER, Associate Professor of Computer Science and Engineering, University of Washington; Research Manager, Facebook Al Research “This book is the most comprehensive and up-to-date reference on natural language pro cessing since the beginning of the deep learn ing revolution. It covers the basics as well as more advanced materials and will expose its
readers to most of the necessary ingredients of state-of-the-art Al and NLP algorithms.” —RICHARD SOCHER, Chief Scientist, Salesforce “This book provides an excellent introduction to natural language processing, with emphasis on foundational methods and algorithms. I highly recommend it to every serious researcher and student in natural language processing.” —HWEE TOU NG, Professor of Computer Science, National University of Singapore
|
any_adam_object | 1 |
author | Eisenstein, Jacob |
author_GND | (DE-588)1199860433 |
author_facet | Eisenstein, Jacob |
author_role | aut |
author_sort | Eisenstein, Jacob |
author_variant | j e je |
building | Verbundindex |
bvnumber | BV046196356 |
classification_rvk | ES 945 ST 306 |
classification_tum | DAT 710 |
ctrlnum | (OCoLC)1128846302 (DE-599)BVBBV046196356 |
discipline | Sprachwissenschaft Informatik Literaturwissenschaft |
format | Book |
fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03184nam a22004458c 4500</leader><controlfield tag="001">BV046196356</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20240206 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">191014s2019 a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780262042840</subfield><subfield code="9">978-0-262-04284-0</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">0262042843</subfield><subfield code="9">0262042843</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1128846302</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV046196356</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-83</subfield><subfield code="a">DE-20</subfield><subfield code="a">DE-355</subfield><subfield code="a">DE-91G</subfield><subfield code="a">DE-573</subfield><subfield code="a">DE-526</subfield><subfield code="a">DE-B768</subfield><subfield code="a">DE-29T</subfield><subfield code="a">DE-739</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ES 945</subfield><subfield code="0">(DE-625)27935:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 306</subfield><subfield code="0">(DE-625)143654:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 710</subfield><subfield code="2">stub</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Eisenstein, Jacob</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1199860433</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Introduction to natural language processing</subfield><subfield code="c">Jacob Eisenstein</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cambridge, MA</subfield><subfield code="b">The MIT Press</subfield><subfield code="c">[2019]</subfield></datafield><datafield tag="264" ind1=" " ind2="4"><subfield code="c">© 2019</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xiv, 519 Seiten</subfield><subfield code="b">Illustrationen</subfield><subfield code="c">24 cm</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="0" ind2=" "><subfield code="a">Adaptive computation and machine learning series</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">"The book provides a technical perspective on the most contemporary data-driven approaches, focusing on techniques from supervised and unsupervised machine learning. It also includes background in the salient linguistic issues, as well as computational representations and algorithms. The first section of the book explores what can be with individual words. The second section concerns structured representations such as sequences, trees, and graphs. The third section highlights different approaches to the representation and analysis of linguistic meaning. The final section describes three of the most transformative applications of natural language processing: information extraction, machine translation, and text generation. The book describes the technical foundations of the field, including the most relevant machine learning techniques, algorithms, and linguistic representations. From these foundations, it extends to contemporary research in areas such as deep learning. Each chapter contains exercises that include paper-and-pencil analysis of the computational algorithms and linguistic issues, as well as software implementations"--</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Informatik</subfield><subfield code="0">(DE-588)4026894-9</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Sprachverarbeitung</subfield><subfield code="0">(DE-588)4116579-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Natural language processing (Computer science)</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Natural language processing (Computer science)</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Sprachverarbeitung</subfield><subfield code="0">(DE-588)4116579-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Informatik</subfield><subfield code="0">(DE-588)4026894-9</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Regensburg - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=031575612&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Regensburg - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=031575612&sequence=000003&line_number=0002&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Klappentext</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-031575612</subfield></datafield></record></collection> |
id | DE-604.BV046196356 |
illustrated | Illustrated |
indexdate | 2024-07-10T08:37:56Z |
institution | BVB |
isbn | 9780262042840 0262042843 |
language | English |
oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-031575612 |
oclc_num | 1128846302 |
open_access_boolean | |
owner | DE-83 DE-20 DE-355 DE-BY-UBR DE-91G DE-BY-TUM DE-573 DE-526 DE-B768 DE-29T DE-739 |
owner_facet | DE-83 DE-20 DE-355 DE-BY-UBR DE-91G DE-BY-TUM DE-573 DE-526 DE-B768 DE-29T DE-739 |
physical | xiv, 519 Seiten Illustrationen 24 cm |
publishDate | 2019 |
publishDateSearch | 2019 |
publishDateSort | 2019 |
publisher | The MIT Press |
record_format | marc |
series2 | Adaptive computation and machine learning series |
spelling | Eisenstein, Jacob Verfasser (DE-588)1199860433 aut Introduction to natural language processing Jacob Eisenstein Cambridge, MA The MIT Press [2019] © 2019 xiv, 519 Seiten Illustrationen 24 cm txt rdacontent n rdamedia nc rdacarrier Adaptive computation and machine learning series "The book provides a technical perspective on the most contemporary data-driven approaches, focusing on techniques from supervised and unsupervised machine learning. It also includes background in the salient linguistic issues, as well as computational representations and algorithms. The first section of the book explores what can be with individual words. The second section concerns structured representations such as sequences, trees, and graphs. The third section highlights different approaches to the representation and analysis of linguistic meaning. The final section describes three of the most transformative applications of natural language processing: information extraction, machine translation, and text generation. The book describes the technical foundations of the field, including the most relevant machine learning techniques, algorithms, and linguistic representations. From these foundations, it extends to contemporary research in areas such as deep learning. Each chapter contains exercises that include paper-and-pencil analysis of the computational algorithms and linguistic issues, as well as software implementations"-- Informatik (DE-588)4026894-9 gnd rswk-swf Sprachverarbeitung (DE-588)4116579-2 gnd rswk-swf Natural language processing (Computer science) Sprachverarbeitung (DE-588)4116579-2 s Informatik (DE-588)4026894-9 s DE-604 Digitalisierung UB Regensburg - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=031575612&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis Digitalisierung UB Regensburg - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=031575612&sequence=000003&line_number=0002&func_code=DB_RECORDS&service_type=MEDIA Klappentext |
spellingShingle | Eisenstein, Jacob Introduction to natural language processing Informatik (DE-588)4026894-9 gnd Sprachverarbeitung (DE-588)4116579-2 gnd |
subject_GND | (DE-588)4026894-9 (DE-588)4116579-2 |
title | Introduction to natural language processing |
title_auth | Introduction to natural language processing |
title_exact_search | Introduction to natural language processing |
title_full | Introduction to natural language processing Jacob Eisenstein |
title_fullStr | Introduction to natural language processing Jacob Eisenstein |
title_full_unstemmed | Introduction to natural language processing Jacob Eisenstein |
title_short | Introduction to natural language processing |
title_sort | introduction to natural language processing |
topic | Informatik (DE-588)4026894-9 gnd Sprachverarbeitung (DE-588)4116579-2 gnd |
topic_facet | Informatik Sprachverarbeitung |
url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=031575612&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=031575612&sequence=000003&line_number=0002&func_code=DB_RECORDS&service_type=MEDIA |
work_keys_str_mv | AT eisensteinjacob introductiontonaturallanguageprocessing |