www.zak24.pl
INTERNETOWA KSIĘGARNIA NAUKOWO - AKADEMICKA

Feasibility of DeepL, Google and Microsoft MT systems implementation into the translation process

19,99  (w tym 5% VAT)

ISBN: 978-83-8206-099-7

Rok wydania: 2020

Liczba stron: 168

Format: A5

Opis

Feasibility of DeepL, Google and Microsoft MT systems implementation into the translation process

Przekładając Nieprzekładalne IX

Autor: Maciej Kur

Wydawnictwo Uniwersytetu Gdańskiego

 

This book presents the methodology and results of a study designed to determine the feasibility of implementation of some of the most popular, widely available and relatively cheap machine translation systems into translation processes carried out in the English -> Polish language pair. A set of outputs provided by DeepL Translator, Google Neural Machine Translation System and Microsoft Translator engines was collected and processed together with translated and post-edited segments produced by a group of Polish translators. The data were then analyzed with the use of various MT evaluation metrics to determine whether the quality of the outputs and amount of post-editing effort was adequate enough to enable efficient implementation of the analyzed engines into the professional environment.

 

Table of contents

Acknowledgements . .. . 7

Introduction . .. . 9

Chapter 1

The status of research . . . 15

1.1. Basic terms and defi nitions .  . 16

1.2. Fundamental models . . . 18

1.2.1. Direct model . . 18

1.2.2. Indirect models . . .  . 20

1.2.3. Statistical Machine Translation (SMT) . . . 23

1.2.3.1. Word-based SMT . . 23

1.2.3.2. N-gram-based SMT . .. 26

1.2.3.3. Phrase-based SMT . .  . 28

1.2.3.4. Context-based SMT . .  . 29

1.2.4. Neural machine translation . . . . 32

1.2.4.1. Discourse in NMT . . .. 37

1.3. Methods of evaluation . .. . 39

1.3.1. Human evaluation . .  . 40

1.3.1.1. Early methods . .. . 40

1.3.1.2. Accuracy, comprehension, fl uency .  42

1.3.1.3. Segment ranking metrics . .. . 44

1.3.1.4. HTER . .  . 45

1.3.2. Automatic evaluation metrics . .  . 48

1.3.2.1. Word-matching metrics .  . 49

1.3.2.2. BLEU . .. . 51

1.3.2.3. NIST and METEOR . . . 53

1.4. Post-editing . .  . 56

1.4.1. Defi nition and PE-related tasks . .. . 57

1.4.2. Post-editing eff ort . . . 60

1.4.3. Automatic post-editing . . . 63

Chapter 2

Description of the study . .. . 65

2.1. Preparatory stage . . . 66

2.1.1. Data preparation . . . . 66

2.1.2. Workstation preparation . . .. . 68

2.2. Experiment . . . .  . 69

2.2.1. Participants . . . . 69

2.2.2. Task 1 – translation . . . . 70

2.2.3. Task 2 – post-editing . . . 71

2.3. Data analysis . . .. 73

2.3.1. Edit time analysis . . . . 73

2.3.2. HTER analysis . . .. 74

2.3.3. Error analysis . . . .. 76

2.3.4. Quality rankings . . .. . 82

Chapter 3

Results . .  . . 87

3.1. Post-editing eff ort measurement . .. . 87

3.1.1. Edit time analysis . . . . 87

3.1.2. HTER scores . . .. . 91

3.2. Quality evaluation . . . 96

3.2.1. Error analysis . . . 96

3.2.1.1. “Missing Words” category errors . . 98

3.2.1.2. “Word Order” category errors . . . 108

3.2.1.3. “Incorrect Words” category errors . . .. 111

3.2.1.3.1. “Sense” subcategory errors . .. 112

3.2.1.3.2. “Incorrect Form” subcategory . . . 116

3.2.1.3.3. “Style” subcategory errors . . . 121

3.2.1.3.4. “Extra Words” and “Idioms” subcategories . . 123

3.2.1.4. “Unknown Words” category errors . .. 125

3.2.1.5. “Punctuation” category errors . . . 128

3.2.1.6. “Spelling” category errors . .  . 133

3.2.2. Quality rankings . .  . 136

3.2.2.1. Ranking A (traditional translation) . . 137

3.2.2.2. Ranking B (post-editing) . . . 141

3.2.3. Duplicated errors . . . 143

Conclusions . . .  . 149

References . . .. . 155

 

Opinie

Na razie nie ma opinii o produkcie.

Napisz pierwszą opinię o „Feasibility of DeepL, Google and Microsoft MT systems implementation into the translation process”

Twój adres e-mail nie zostanie opublikowany. Wymagane pola są oznaczone *