Neural machine translation:
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Cambridge
Cambridge University Press
2020
|
| Ausgabe: | First published |
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Beschreibung: | XIV, 393 Seiten Illustrationen, Diagramme |
| ISBN: | 9781108497329 |
Internformat
MARC
| LEADER | 00000nam a2200000zc 4500 | ||
|---|---|---|---|
| 001 | BV046839075 | ||
| 003 | DE-604 | ||
| 005 | 20230412 | ||
| 007 | t | ||
| 008 | 200805s2020 a||| |||| 00||| eng d | ||
| 020 | |a 9781108497329 |9 978-1-10849-732-9 | ||
| 035 | |a (OCoLC)1225978081 | ||
| 035 | |a (DE-599)BVBBV046839075 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-1043 |a DE-739 | ||
| 084 | |a ES 960 |0 (DE-625)27938: |2 rvk | ||
| 100 | 1 | |a Koehn, Philipp |d 1971- |e Verfasser |0 (DE-588)140284745 |4 aut | |
| 245 | 1 | 0 | |a Neural machine translation |c Philipp Koehn (Johns Hopkins University) |
| 250 | |a First published | ||
| 264 | 1 | |a Cambridge |b Cambridge University Press |c 2020 | |
| 300 | |a XIV, 393 Seiten |b Illustrationen, Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 650 | 0 | 7 | |a Neuronales Netz |0 (DE-588)4226127-2 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelle Übersetzung |0 (DE-588)4003966-3 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Maschinelle Übersetzung |0 (DE-588)4003966-3 |D s |
| 689 | 0 | 1 | |a Neuronales Netz |0 (DE-588)4226127-2 |D s |
| 689 | 0 | |5 DE-604 | |
| 776 | 0 | 8 | |i Erscheint auch als |n Online-Ausgabe |z 978-1-108-60848-0 |
| 856 | 4 | 2 | |m Digitalisierung UB Passau - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032248083&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-032248083 | ||
Datensatz im Suchindex
| _version_ | 1804181666586951680 |
|---|---|
| adam_text | Contents Preface Reading Guide Part I 1 The Translation Problem 1.1 1.2 1.3 1.4 1.5 2 3 4 Coals of Translation Ambiguity The Linguistic View The Data View Practical Issues 1 3 4 5 8 11 15 Uses of Machine Translation 19 2.1 2.2 2.3 2.4 2.5 19 20 23 26 27 Information Access Aiding Human Translators Communication Natural Language Processing Pipelines Multimodal MachineTranslation History 29 3.1 3.2 30 33 Neural Networks Machine Translation Evaluation 41 4.1 4.2 4.3 4.4 41 45 52 59 Part II 5 Introduction page xi xiii Task-Based Evaluation Human Assessments Automatic Metrics Metrics Research Basics Neural Networks 5.1 5.2 Linear Models Multiple Layers 65 67 67 68 vii
viii Contents 5.3 5.4 5.5 5.6 5.7 Nonlinearity Inference Back-Propagation Training Exploiting Parallel Processing Hands On: Neural Networks in Python Computation Graphs 6.1 Neural Networks as Computation Graphs 6.2 Gradient Computations 6.3 Hands On: Deep Learning Frameworks Neural Language Models 7.1 Feed-Forward Neural Language Models 7.2 Word Embeddings 7.3 Noise Contrastive Estimation 7.4 Recurrent Neural Language Models Long Short-Term Memory Models 7.5 7.6 Gated Recurrent Units 7.7 Deep Models 7.8 Hands On: Neural Language Models in PyTorch 7.9 Further Readings 69 70 72 79 80 89 89 91 95 103 103 107 109 110 112 115 116 118 123 Neural Translation Models Encoder-Decoder Approach 8.1 Adding an Alignment Model 8.2 Training 8.3 8.4 Deep Models Hands On: Neural Translation Models 8.5 in PyTorch 8.6 Further Readings 125 125 126 130 133 Decoding Beam Search 9.1 Ensemble Decoding 9.2 9.3 Reranking Optimizing Decoding 9.4 Directing Decoding 9.5 9.6 Hands On: Decoding in Python 9.7 Further Readings 143 143 147 148 154 155 158 163 136 141
Contents Part III Refinements 10 Machine Learning Tricks 10.1 10.2 10.3 10.4 10.5 10.6 10.7 Failures in Machine Learning Ensuring Randomness Adjusting the Learning Rate Avoiding Local Optima Addressing Vanishing and Exploding Gradients Sentence-Level Optimization Further Readings 11 Alternate Architectures 11.1 11.2 11.3 11.4 11.5 11.6 Components of Neural Networks Attention Models Convolutional Machine Translation Convolutional Neural Networks with Attention Self-Attention: Transformer Further Readings 12 Revisiting Words 12.1 12.2 12.3 12.4 12.5 Word Embeddings Multilingual Word Embeddings Large Vocabularies Character-Based Models Further Readings 13 Adaptation 13.1 13.2 13.3 13.4 13.5 Domains Mixture Models Subsampling Fine-Tuning Further Readings 14 Beyond Parallel Corpora 14.1 14.2 14.3 14.4 Using Monolingual Data Multiple Language Pairs Training on Related Tasks Further Readings 15 Linguistic Structure 15.1 15.2 Guided Alignment Training Modeling Coverage 169 171 171 174 176 179 182 186 189 193 193 199 203 205 207 211 213 214 220 224 229 233 239 239 245 249 253 257 263 264 269 272 274 281 282 284 ix
x Contents 15.3 15.4 Adding Linguistic Annotation Further Readings 16 Current Challenges 16.1 16.2 16.3 16.4 16.5 16.6 16.7 Domain Mismatch Amount of Training Data Rare Words Noisy Data Beam Search Word Alignment Further Readings 17 Analysis and Visualization 17.1 17.2 17.3 17.4 17.5 17.6 Error Analysis Visualization Probing Representations Identifying Neurons Tracing Decisions Back to Inputs Further Readings Bibliography Author Index Index 287 290 293 294 295 296 299 304 306 307 311 311 319 328 329 332 337 343 375 385
|
| adam_txt |
Contents Preface Reading Guide Part I 1 The Translation Problem 1.1 1.2 1.3 1.4 1.5 2 3 4 Coals of Translation Ambiguity The Linguistic View The Data View Practical Issues 1 3 4 5 8 11 15 Uses of Machine Translation 19 2.1 2.2 2.3 2.4 2.5 19 20 23 26 27 Information Access Aiding Human Translators Communication Natural Language Processing Pipelines Multimodal MachineTranslation History 29 3.1 3.2 30 33 Neural Networks Machine Translation Evaluation 41 4.1 4.2 4.3 4.4 41 45 52 59 Part II 5 Introduction page xi xiii Task-Based Evaluation Human Assessments Automatic Metrics Metrics Research Basics Neural Networks 5.1 5.2 Linear Models Multiple Layers 65 67 67 68 vii
viii Contents 5.3 5.4 5.5 5.6 5.7 Nonlinearity Inference Back-Propagation Training Exploiting Parallel Processing Hands On: Neural Networks in Python Computation Graphs 6.1 Neural Networks as Computation Graphs 6.2 Gradient Computations 6.3 Hands On: Deep Learning Frameworks Neural Language Models 7.1 Feed-Forward Neural Language Models 7.2 Word Embeddings 7.3 Noise Contrastive Estimation 7.4 Recurrent Neural Language Models Long Short-Term Memory Models 7.5 7.6 Gated Recurrent Units 7.7 Deep Models 7.8 Hands On: Neural Language Models in PyTorch 7.9 Further Readings 69 70 72 79 80 89 89 91 95 103 103 107 109 110 112 115 116 118 123 Neural Translation Models Encoder-Decoder Approach 8.1 Adding an Alignment Model 8.2 Training 8.3 8.4 Deep Models Hands On: Neural Translation Models 8.5 in PyTorch 8.6 Further Readings 125 125 126 130 133 Decoding Beam Search 9.1 Ensemble Decoding 9.2 9.3 Reranking Optimizing Decoding 9.4 Directing Decoding 9.5 9.6 Hands On: Decoding in Python 9.7 Further Readings 143 143 147 148 154 155 158 163 136 141
Contents Part III Refinements 10 Machine Learning Tricks 10.1 10.2 10.3 10.4 10.5 10.6 10.7 Failures in Machine Learning Ensuring Randomness Adjusting the Learning Rate Avoiding Local Optima Addressing Vanishing and Exploding Gradients Sentence-Level Optimization Further Readings 11 Alternate Architectures 11.1 11.2 11.3 11.4 11.5 11.6 Components of Neural Networks Attention Models Convolutional Machine Translation Convolutional Neural Networks with Attention Self-Attention: Transformer Further Readings 12 Revisiting Words 12.1 12.2 12.3 12.4 12.5 Word Embeddings Multilingual Word Embeddings Large Vocabularies Character-Based Models Further Readings 13 Adaptation 13.1 13.2 13.3 13.4 13.5 Domains Mixture Models Subsampling Fine-Tuning Further Readings 14 Beyond Parallel Corpora 14.1 14.2 14.3 14.4 Using Monolingual Data Multiple Language Pairs Training on Related Tasks Further Readings 15 Linguistic Structure 15.1 15.2 Guided Alignment Training Modeling Coverage 169 171 171 174 176 179 182 186 189 193 193 199 203 205 207 211 213 214 220 224 229 233 239 239 245 249 253 257 263 264 269 272 274 281 282 284 ix
x Contents 15.3 15.4 Adding Linguistic Annotation Further Readings 16 Current Challenges 16.1 16.2 16.3 16.4 16.5 16.6 16.7 Domain Mismatch Amount of Training Data Rare Words Noisy Data Beam Search Word Alignment Further Readings 17 Analysis and Visualization 17.1 17.2 17.3 17.4 17.5 17.6 Error Analysis Visualization Probing Representations Identifying Neurons Tracing Decisions Back to Inputs Further Readings Bibliography Author Index Index 287 290 293 294 295 296 299 304 306 307 311 311 319 328 329 332 337 343 375 385 |
| any_adam_object | 1 |
| any_adam_object_boolean | 1 |
| author | Koehn, Philipp 1971- |
| author_GND | (DE-588)140284745 |
| author_facet | Koehn, Philipp 1971- |
| author_role | aut |
| author_sort | Koehn, Philipp 1971- |
| author_variant | p k pk |
| building | Verbundindex |
| bvnumber | BV046839075 |
| classification_rvk | ES 960 |
| ctrlnum | (OCoLC)1225978081 (DE-599)BVBBV046839075 |
| discipline | Sprachwissenschaft Literaturwissenschaft |
| discipline_str_mv | Sprachwissenschaft Literaturwissenschaft |
| edition | First published |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01500nam a2200361zc 4500</leader><controlfield tag="001">BV046839075</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20230412 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">200805s2020 a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781108497329</subfield><subfield code="9">978-1-10849-732-9</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1225978081</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV046839075</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-1043</subfield><subfield code="a">DE-739</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ES 960</subfield><subfield code="0">(DE-625)27938:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Koehn, Philipp</subfield><subfield code="d">1971-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)140284745</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Neural machine translation</subfield><subfield code="c">Philipp Koehn (Johns Hopkins University)</subfield></datafield><datafield tag="250" ind1=" " ind2=" "><subfield code="a">First published</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cambridge</subfield><subfield code="b">Cambridge University Press</subfield><subfield code="c">2020</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">XIV, 393 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</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="650" ind1="0" ind2="7"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelle Übersetzung</subfield><subfield code="0">(DE-588)4003966-3</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Maschinelle Übersetzung</subfield><subfield code="0">(DE-588)4003966-3</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Online-Ausgabe</subfield><subfield code="z">978-1-108-60848-0</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Passau - 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=032248083&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-032248083</subfield></datafield></record></collection> |
| id | DE-604.BV046839075 |
| illustrated | Illustrated |
| index_date | 2024-07-03T15:07:29Z |
| indexdate | 2024-07-10T08:55:17Z |
| institution | BVB |
| isbn | 9781108497329 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-032248083 |
| oclc_num | 1225978081 |
| open_access_boolean | |
| owner | DE-1043 DE-739 |
| owner_facet | DE-1043 DE-739 |
| physical | XIV, 393 Seiten Illustrationen, Diagramme |
| publishDate | 2020 |
| publishDateSearch | 2020 |
| publishDateSort | 2020 |
| publisher | Cambridge University Press |
| record_format | marc |
| spelling | Koehn, Philipp 1971- Verfasser (DE-588)140284745 aut Neural machine translation Philipp Koehn (Johns Hopkins University) First published Cambridge Cambridge University Press 2020 XIV, 393 Seiten Illustrationen, Diagramme txt rdacontent n rdamedia nc rdacarrier Neuronales Netz (DE-588)4226127-2 gnd rswk-swf Maschinelle Übersetzung (DE-588)4003966-3 gnd rswk-swf Maschinelle Übersetzung (DE-588)4003966-3 s Neuronales Netz (DE-588)4226127-2 s DE-604 Erscheint auch als Online-Ausgabe 978-1-108-60848-0 Digitalisierung UB Passau - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032248083&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Koehn, Philipp 1971- Neural machine translation Neuronales Netz (DE-588)4226127-2 gnd Maschinelle Übersetzung (DE-588)4003966-3 gnd |
| subject_GND | (DE-588)4226127-2 (DE-588)4003966-3 |
| title | Neural machine translation |
| title_auth | Neural machine translation |
| title_exact_search | Neural machine translation |
| title_exact_search_txtP | Neural machine translation |
| title_full | Neural machine translation Philipp Koehn (Johns Hopkins University) |
| title_fullStr | Neural machine translation Philipp Koehn (Johns Hopkins University) |
| title_full_unstemmed | Neural machine translation Philipp Koehn (Johns Hopkins University) |
| title_short | Neural machine translation |
| title_sort | neural machine translation |
| topic | Neuronales Netz (DE-588)4226127-2 gnd Maschinelle Übersetzung (DE-588)4003966-3 gnd |
| topic_facet | Neuronales Netz Maschinelle Übersetzung |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=032248083&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT koehnphilipp neuralmachinetranslation |