Statistical Machine Translation Part IV Decoding Alexander Fraser

  • Slides: 36
Download presentation
Statistical Machine Translation Part IV – Decoding Alexander Fraser CIS, LMU München 2014. 11.

Statistical Machine Translation Part IV – Decoding Alexander Fraser CIS, LMU München 2014. 11. 04 WSD and MT

Outline • Phrase-based translation model • Decoding – Basic phrase-based decoding – Dealing with

Outline • Phrase-based translation model • Decoding – Basic phrase-based decoding – Dealing with complexity • Recombination • Pruning • Future cost estimation

Slide from Koehn 2008

Slide from Koehn 2008

d Modified from Koehn 2008

d Modified from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Decoding • Goal: find the best target translation of a source sentence • Involves

Decoding • Goal: find the best target translation of a source sentence • Involves search – Find maximum probability path in a dynamically generated search graph • Generate English string, from left to right, by covering parts of Foreign string – Generating English string left to right allows scoring with the n-gram language model • Here is an example of one path

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

(possible future paths are the same) Modified from Koehn 2008

(possible future paths are the same) Modified from Koehn 2008

(possible future paths are the same) Modified from Koehn 2008

(possible future paths are the same) Modified from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

Slide from Koehn 2008

NLP Machine Translation Decoding Decoding Find a translationNLP Machine Translation Decoding Decoding Find a translation
Statistical Machine Translation Part I Introduction Alexander FraserStatistical Machine Translation Part I Introduction Alexander Fraser
Statistical Machine Translation Part I Introduction Alexander FraserStatistical Machine Translation Part I Introduction Alexander Fraser
Statistical Machine Translation Part I Introduction Alexander FraserStatistical Machine Translation Part I Introduction Alexander Fraser
Statistical Machine Translation Part I Introduction Alexander FraserStatistical Machine Translation Part I Introduction Alexander Fraser
Statistical Machine Translation Part I Introduction Alexander FraserStatistical Machine Translation Part I Introduction Alexander Fraser
Statistical Machine Translation Raghav Bashyal Statistical Machine TranslationStatistical Machine Translation Raghav Bashyal Statistical Machine Translation
Royal Fraser Freedom Fraser and Mr Fraser ByRoyal Fraser Freedom Fraser and Mr Fraser By
Statistical Machine Translation Part I Introduction Alex FraserStatistical Machine Translation Part I Introduction Alex Fraser
Statistical Machine Translation Part III Phrasebased SMT DecodingStatistical Machine Translation Part III Phrasebased SMT Decoding
Statistical Machine Translation Part III Phrasebased SMT DecodingStatistical Machine Translation Part III Phrasebased SMT Decoding
Machine Translation MT ComputerAssisted Translation CAT Machine TranslationMachine Translation MT ComputerAssisted Translation CAT Machine Translation
Introduction to Translation Machine Computerassisted Translation Machine TranslationIntroduction to Translation Machine Computerassisted Translation Machine Translation
Introduction to Translation Machine Computerassisted Translation Machine TranslationIntroduction to Translation Machine Computerassisted Translation Machine Translation
Statistical Machine Translation Machine Translation Pyramid RBMT RuleBasedStatistical Machine Translation Machine Translation Pyramid RBMT RuleBased
Finite State Morphology Alexander Fraser Liane Guillou fraserFinite State Morphology Alexander Fraser Liane Guillou fraser
Statistical Machine Translation Part IV LogLinear Models AlexanderStatistical Machine Translation Part IV LogLinear Models Alexander
Statistical Machine Translation Part V Phrasebased SMT AlexanderStatistical Machine Translation Part V Phrasebased SMT Alexander
Statistical Machine Translation Part IV LogLinear Models AlexanderStatistical Machine Translation Part IV LogLinear Models Alexander
Statistical Machine Translation Part IIIb Phrasebased Model AlexanderStatistical Machine Translation Part IIIb Phrasebased Model Alexander
Statistical Machine Translation Part III ManytoMany Alignments AlexanderStatistical Machine Translation Part III ManytoMany Alignments Alexander
Statistical Machine Translation Part III Phrasebased SMT AlexanderStatistical Machine Translation Part III Phrasebased SMT Alexander
Statistical Machine Translation Part IV LogLinear Models AlexanderStatistical Machine Translation Part IV LogLinear Models Alexander
Statistical Machine Translation Part III ManytoMany Alignments AlexanderStatistical Machine Translation Part III ManytoMany Alignments Alexander