Statistical language models with structural elements:
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
2004
|
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Beschreibung: | München, Techn. Univ., Diss., 2004 |
| Beschreibung: | X, 108 S. graph. Darst. |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV019813293 | ||
| 003 | DE-604 | ||
| 005 | 20060809 | ||
| 007 | t | ||
| 008 | 050518s2004 d||| m||| 00||| eng d | ||
| 035 | |a (OCoLC)61144887 | ||
| 035 | |a (DE-599)BVBBV019813293 | ||
| 040 | |a DE-604 |b ger |e rakwb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-91 |a DE-29T |a DE-12 |a DE-706 |a DE-83 | ||
| 084 | |a ELT 532d |2 stub | ||
| 084 | |a ELT 533d |2 stub | ||
| 084 | |a ELT 505d |2 stub | ||
| 100 | 1 | |a Weilhammer, Karl |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Statistical language models with structural elements |c Karl Weilhammer |
| 264 | 1 | |c 2004 | |
| 300 | |a X, 108 S. |b graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a München, Techn. Univ., Diss., 2004 | ||
| 650 | 0 | 7 | |a Informationstheoretisches Modell |0 (DE-588)4161675-3 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Sprachsignal |0 (DE-588)4056494-0 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Stochastischer Prozess |0 (DE-588)4057630-9 |2 gnd |9 rswk-swf |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 689 | 0 | 0 | |a Sprachsignal |0 (DE-588)4056494-0 |D s |
| 689 | 0 | 1 | |a Stochastischer Prozess |0 (DE-588)4057630-9 |D s |
| 689 | 0 | 2 | |a Informationstheoretisches Modell |0 (DE-588)4161675-3 |D s |
| 689 | 0 | |5 DE-604 | |
| 856 | 4 | 2 | |m GBV Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=013138682&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-013138682 | ||
Datensatz im Suchindex
| _version_ | 1804133312641368064 |
|---|---|
| adam_text | CONTENTS ZUSAMMENFASSUNG III ABSTRACT V CONTENTS IX 1 INTRODUCTION 1 1.1
APPLICATIONS 1 1.1.1 AUTOMATIC SPEECH RECOGNITION 1 1.1.2 TEXT
COMPRESSION 2 1.2 STRUCTURAL ELEMENTS 2 1.3 GENERALISATION OF UNOBSERVED
BIGRAMS 3 2 METRICS FOR SPEECH AND LANGUAGE 5 2.1 LIKELIHOOD 5 2.2
PERPLEXITY 6 3 STATE OF THE ART IN LANGUAGE MODELLING 9 3.1 THE MAXIMUM
LIKELIHOOD ESTIMATION 9 3.2 SMOOTHING WITH LOWER ORDER N-GRAM
DISTRIBUTIONS 10 3.2.1 GOOD-TURING AND KATZ DISCOUNTING 11 3.2.2
WITTEN-BELL DISCOUNTING 12 3.2.3 KNESER-NEY SMOOTHING 12 3.3 CLUSTERING
13 3.3.1 N-GRAM CLASS MODEIS 14 3.3.2 DISTRIBUTIONAL CLUSTERING 15 3.3.3
SIMILARITY-BASED MODEIS 17 3.4 PHRASE UNIT MODEIS 18 3.4.1 THE MULTIGRAM
MODEL 18 3.4.2 STRUCTURAL AND CLASS PHRASE MODEL 20 3.5 BEYOND N-GRAMS
20 VII VIII CONTENTS 3.5.1 LONG-RANGE AND ADAPTIVE MODEIS 21 3.5.2
CLASSIFICATION TECHNIQUES AS LANGUAGE MODEIS 21 3.5.3 PROBABILISTIC
GRAMMARS 22 3.5.4 INTEGRATION OF DIFFERENT TECHNIQUES 23 4 THE
STRUCTURAL DEMENT MODEL 25 4.1 PROBABILITY DISTRIBUTIONS 26 4.1.1
REST-ELEMENT MODEIS 26 4.1.2 WITTEN-BELL REST-ELEMENT MODEIS 27 4.2 THE
ALGORITHM 29 4.2.1 CALCULATION OF TEST SET LIKELIHOOD 29 4.2.2 THE
TRAINING ALGORITHM 30 4.2.3 FAST CALCULATION 32 4.2.4 COMPLEXITY 38 4.3
IMPLEMENTATION 39 5 EXPERIMENTS * STRUCTURAL ELEMENT MODEIS 41 5.1 THE
DATA FOR TRAINING AND TESTING 41 5.2 ALGORITHM USED FOR EXPERIMENTS 42
5.3 INFLUENCE OF PARAMETERS ON THE REST ELEMENT MODEL 42 5.3.1 DISCOUNT
VALUE 42 5.3.2 THE INFLUENCE OF DISCOUNT VALUE AND SIZE OF THE TRAINING
SET ON THE STRUCTURAL ELEMENT DISTRIBUTION IN THE TRAINING DATA . . . .
47 5.3.3 BETTER BIGRAM COVERAGE BY INCLUDING THE BIGRAMS OF CROSS-
VALIDATION SET AND DEVELOPMENT TEST SET 49 5.3.4 THE REST-ELEMENT MODEL
WITH TWO DISCOUNT PARAMETERS 53 5.4 MODELS INSPIRED BY WITTEN-BELL
DISCOUNTING 55 5.5 DIFFERENT NUMBERS OF STRUCTURAL ELEMENTS 57 5.6 LEAVE
ONE OUT TRAINING 59 5.6.1 PERPLEXITIES 59 5.6.2 CONVERGENCE OF THE
LEAVE-ONE-OUT MODEL 61 5.7 ARE STRUCTURAL ELEMENTS MEANINGFUL? 63 6 THE
STRUCTURAL ELEMENT HMM 65 6.1 GENERAL HIDDEN MARKOV MODELS 65 6.1.1
DEFINITION 66 6.1.2 THE FORWARD-BACKWARD CALCULATION OF THE LIKELIHOOD
66 6.1.3 BAUM-WELCH RE-ESTIMATION ALGORITHM 68 6.2 THE MODEL TOPOLOGY 72
CONTENTS I X 6.2.1 INFERENCE AND PARAMETER ESTIMATION 73 6.2.2 THE
TREATMENT OF UNKNOWN WORDS 75 7 EXPERIMENTS WITH THE HMM REALISATION 77
7.1 IMPLEMENTATION AND CORPUS 77 7.2 INFIUENCE OF THE NUMBER OF
STRUCTURAL ELEMENTS 78 7.3 INFIUENCE OF THE INFERENCE CONSTANT 79 8
COMPARISON WITH STANDARD MODEIS 81 8.1 REFERENCE MODEIS 81 8.2
STRUCTURAL ELEMENT MODEIS 82 8.3 RESULTS 83 9 CONCLUSION 85 A FORMAL
DEFINITIONS 89 B ADDITIONAL PROBABILITY DISTRIBUTIONS 91 B.L BACK-OFF
MODEL 91 B.2 WITTEN-BELL BACK-OFF MODEL 91 B.3 APPROXIMATIVE WITTEN-BELL
REST-ELEMENT MODEL 92 B.4 PLACEWAY S WITTEN-BELL MODEL 93 C PROOF OF
RE-ESTIMATION FORMULA 95 D HARD CLUSTERING IN THE STRUCTURAL ELEMENT
MODEL 97 ACKNOWLEDGEMENTS 99 BIBLIOGRAPHY 100
|
| any_adam_object | 1 |
| author | Weilhammer, Karl |
| author_facet | Weilhammer, Karl |
| author_role | aut |
| author_sort | Weilhammer, Karl |
| author_variant | k w kw |
| building | Verbundindex |
| bvnumber | BV019813293 |
| classification_tum | ELT 532d ELT 533d ELT 505d |
| ctrlnum | (OCoLC)61144887 (DE-599)BVBBV019813293 |
| discipline | Elektrotechnik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01564nam a2200397 c 4500</leader><controlfield tag="001">BV019813293</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20060809 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">050518s2004 d||| m||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)61144887</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV019813293</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91</subfield><subfield code="a">DE-29T</subfield><subfield code="a">DE-12</subfield><subfield code="a">DE-706</subfield><subfield code="a">DE-83</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ELT 532d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ELT 533d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ELT 505d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Weilhammer, Karl</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Statistical language models with structural elements</subfield><subfield code="c">Karl Weilhammer</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2004</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">X, 108 S.</subfield><subfield code="b">graph. Darst.</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="500" ind1=" " ind2=" "><subfield code="a">München, Techn. Univ., Diss., 2004</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Informationstheoretisches Modell</subfield><subfield code="0">(DE-588)4161675-3</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Sprachsignal</subfield><subfield code="0">(DE-588)4056494-0</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Stochastischer Prozess</subfield><subfield code="0">(DE-588)4057630-9</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Sprachsignal</subfield><subfield code="0">(DE-588)4056494-0</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Stochastischer Prozess</subfield><subfield code="0">(DE-588)4057630-9</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Informationstheoretisches Modell</subfield><subfield code="0">(DE-588)4161675-3</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">GBV Datenaustausch</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=013138682&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:BVB01-013138682</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV019813293 |
| illustrated | Illustrated |
| indexdate | 2024-07-09T20:06:43Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-013138682 |
| oclc_num | 61144887 |
| open_access_boolean | |
| owner | DE-91 DE-BY-TUM DE-29T DE-12 DE-706 DE-83 |
| owner_facet | DE-91 DE-BY-TUM DE-29T DE-12 DE-706 DE-83 |
| physical | X, 108 S. graph. Darst. |
| publishDate | 2004 |
| publishDateSearch | 2004 |
| publishDateSort | 2004 |
| record_format | marc |
| spelling | Weilhammer, Karl Verfasser aut Statistical language models with structural elements Karl Weilhammer 2004 X, 108 S. graph. Darst. txt rdacontent n rdamedia nc rdacarrier München, Techn. Univ., Diss., 2004 Informationstheoretisches Modell (DE-588)4161675-3 gnd rswk-swf Sprachsignal (DE-588)4056494-0 gnd rswk-swf Stochastischer Prozess (DE-588)4057630-9 gnd rswk-swf (DE-588)4113937-9 Hochschulschrift gnd-content Sprachsignal (DE-588)4056494-0 s Stochastischer Prozess (DE-588)4057630-9 s Informationstheoretisches Modell (DE-588)4161675-3 s DE-604 GBV Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=013138682&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Weilhammer, Karl Statistical language models with structural elements Informationstheoretisches Modell (DE-588)4161675-3 gnd Sprachsignal (DE-588)4056494-0 gnd Stochastischer Prozess (DE-588)4057630-9 gnd |
| subject_GND | (DE-588)4161675-3 (DE-588)4056494-0 (DE-588)4057630-9 (DE-588)4113937-9 |
| title | Statistical language models with structural elements |
| title_auth | Statistical language models with structural elements |
| title_exact_search | Statistical language models with structural elements |
| title_full | Statistical language models with structural elements Karl Weilhammer |
| title_fullStr | Statistical language models with structural elements Karl Weilhammer |
| title_full_unstemmed | Statistical language models with structural elements Karl Weilhammer |
| title_short | Statistical language models with structural elements |
| title_sort | statistical language models with structural elements |
| topic | Informationstheoretisches Modell (DE-588)4161675-3 gnd Sprachsignal (DE-588)4056494-0 gnd Stochastischer Prozess (DE-588)4057630-9 gnd |
| topic_facet | Informationstheoretisches Modell Sprachsignal Stochastischer Prozess Hochschulschrift |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=013138682&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT weilhammerkarl statisticallanguagemodelswithstructuralelements |