SlideShare a Scribd company logo
1 of 21
Neural MT
Separating the hype from reality
a report from the front line
TAUS Webinar / Industry Leaders Forum / LocWorld 34
The Neural Narrative
Great, thanks. Let me use it now…
LevelofDifficulty
Korean
Japanese
French IT
Marketing
Patent
Gisting
PEMT
Perfect
German
Use caseIndustryLanguage
Use cases for machine translation
Impact of Neural MT
Use cases covered by generic MT
Use cases needing custom MTThe
Bar
Impact of Neural MT
Use cases covered by generic MT
Use cases needing custom MTThe
Bar
Neural
MT has
raised the
bar
Of course.
We’re a team of MT experts. This is a big part of the value that
we bring to the table. We’re not just taking open-source tools off
the shelf. We’re innovating, researching, developing new
processes. Same for Neural MT.
e.g. lexically constrained decoding
Neural MT @ Iconic
“Do you ‘do’ Neural MT?”
It’s one of the ways.
MT is not a one-size-fits-all technology. What constitutes the best
approach depends on the language pair, domain, use case, and
various other factors. In some cases, the best approach will be
Neural MT, but not yet all the time.
Neural MT @ Iconic
“Is this the way you do MT now?”
When it gives the best output!
When you’re customising MT, there are so many things you can
do – different processors, parameters, ways of combining data
and tuning. We try multiple approaches and allow our systems to
use the best one.
Let’s look at some case studies, but first…
Neural MT @ Iconic
“When do you use it then?”
The Iconic Ensemble Architecture™
Patents Case Study
Average length: 7 words
Average length: 30 words
3 languages Same data sets Client evaluation
Ranking
1. Unusable
2. Poor
3. Adequate
4. Good
5. Excellent
Criteria
90% Adequate or above
0% Unusable
Linguist Review
both pass title criteria
only Iconic MT passed
abstracts
Patents Case Study – Chinese to English
31
3938
19
0
5
10
15
20
25
30
35
40
45
Titles Abstracts
Iconic MT Iconic Neural MT
Outcome
Iconic MT deployed in
production
Linguist Review
both passed on titles
only NMT passed abstracts
Patents Case Study – Japanese to English
52
33
0
10
20
30
40
50
60
Titles Abstracts
Iconic MT Iconic Neural MT
Outcome
Iconic MT deployed for titles
Neural MT deployed for
abstracts
4
5
4
4
Patents Case Study – Korean to English
40
25
0
5
10
15
20
25
30
35
40
45
Titles Abstracts
Iconic MT Iconic Neural MT
Linguist Review
Iconic MT below criteria
Neural MT significantly better
Outcome
Under review!
2
6
4
3
Neural MT raises the bar for general purpose MT
but the bar still needs to be tested.
Customisation Case Study
English to French English to Hindi
BLEU 1-TER BLEU 1-TER
Iconic MT 43.0 (+10.4) 55.2 (+7.7) 46.75 (+12.96) 56.4 (+5.5)
GNMT 32.6 47.5 33.79 50.9
Iconic NMT 39.2 50.5 - -
2 languages 1.5M training segments IT content
The Iconic Ensemble Architecture™
Neural MT is another
powerful tool in our
arsenal that helps us
deliver best-in-class
machine translation
output
“I don’t give a damn
what you do!”
MT @ Iconic – what we don’t do
MT MT MT MT
MT
MTMT
MTMTMTMTMT
MTMTMTMTMTMT
The ability to build your own MT
engines with Moses, Phrasal,
OpenNMT, Nematus, Fairseq.
Provide off-the-shelf general
industry engines. There are
some very adequate solutions for
that!
MT
Customised expert-built MT, using
the most appropriate tool for the job,
MT or otherwise.
MT @ Iconic – what we do do!
Develop products and solutions that
incorporate machine translation –
not just access to an API.
Engage our expert team on an Neural MT project to see if it works for your content
Neural MT – Early Adopter Program
To date
Custom-developments with
some of our closest partners
Now
Inviting early adopters to
expand the range of casesEarly Adopter Program
Thank You!
john@iconictranslation.com
@johntins / @iconictrans

More Related Content

What's hot

From the Lab to the Market: Commercialising MT Research
From the Lab to the Market: Commercialising MT ResearchFrom the Lab to the Market: Commercialising MT Research
From the Lab to the Market: Commercialising MT ResearchIconic Translation Machines
 
9. Ethics - Juan Jose Arevalillo Doval (Hermes)
9. Ethics - Juan Jose Arevalillo Doval (Hermes)9. Ethics - Juan Jose Arevalillo Doval (Hermes)
9. Ethics - Juan Jose Arevalillo Doval (Hermes)RIILP
 
Learn the different approaches to machine translation and how to improve the ...
Learn the different approaches to machine translation and how to improve the ...Learn the different approaches to machine translation and how to improve the ...
Learn the different approaches to machine translation and how to improve the ...SDL
 
kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...
kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...
kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...Manuel Herranz
 
6. Entrepreneurship - Juan Jose Arevalillo Doval (Hermes)
6. Entrepreneurship - Juan Jose Arevalillo Doval (Hermes)6. Entrepreneurship - Juan Jose Arevalillo Doval (Hermes)
6. Entrepreneurship - Juan Jose Arevalillo Doval (Hermes)RIILP
 
High Volume, Rapid Turn Around Localization: Lessons Learned
High Volume, Rapid Turn Around Localization: Lessons LearnedHigh Volume, Rapid Turn Around Localization: Lessons Learned
High Volume, Rapid Turn Around Localization: Lessons LearnedSDL
 
Carla Parra Escartin - ER2 Hermes Traducciones
Carla Parra Escartin - ER2 Hermes Traducciones Carla Parra Escartin - ER2 Hermes Traducciones
Carla Parra Escartin - ER2 Hermes Traducciones RIILP
 
12. Gloria Corpas, Jorge Leiva, Miriam Seghiri (UMA) Human Translation & Tran...
12. Gloria Corpas, Jorge Leiva, Miriam Seghiri (UMA) Human Translation & Tran...12. Gloria Corpas, Jorge Leiva, Miriam Seghiri (UMA) Human Translation & Tran...
12. Gloria Corpas, Jorge Leiva, Miriam Seghiri (UMA) Human Translation & Tran...RIILP
 
Guideline for project writing
Guideline for project writingGuideline for project writing
Guideline for project writingsuryakantbhonge
 
VOC real world enterprise needs
VOC real world enterprise needsVOC real world enterprise needs
VOC real world enterprise needsIvan Berlocher
 
10. Lucia Specia (USFD) Evaluation of Machine Translation
10. Lucia Specia (USFD) Evaluation of Machine Translation10. Lucia Specia (USFD) Evaluation of Machine Translation
10. Lucia Specia (USFD) Evaluation of Machine TranslationRIILP
 
The I in PRIMM - Code Comprehension and Questioning
The I in PRIMM - Code Comprehension and QuestioningThe I in PRIMM - Code Comprehension and Questioning
The I in PRIMM - Code Comprehension and QuestioningSue Sentance
 
Welocalize Throughputs and Post-Editing Productivity Webinar Laura Casanellas
Welocalize Throughputs and Post-Editing Productivity Webinar Laura CasanellasWelocalize Throughputs and Post-Editing Productivity Webinar Laura Casanellas
Welocalize Throughputs and Post-Editing Productivity Webinar Laura CasanellasWelocalize
 
18. Alessandro Cattelan (Translated) Terminology
18. Alessandro Cattelan (Translated) Terminology18. Alessandro Cattelan (Translated) Terminology
18. Alessandro Cattelan (Translated) TerminologyRIILP
 
DCXS best selfcare-solutions DynamicFAQ
DCXS best selfcare-solutions DynamicFAQDCXS best selfcare-solutions DynamicFAQ
DCXS best selfcare-solutions DynamicFAQLilianBernardin
 

What's hot (15)

From the Lab to the Market: Commercialising MT Research
From the Lab to the Market: Commercialising MT ResearchFrom the Lab to the Market: Commercialising MT Research
From the Lab to the Market: Commercialising MT Research
 
9. Ethics - Juan Jose Arevalillo Doval (Hermes)
9. Ethics - Juan Jose Arevalillo Doval (Hermes)9. Ethics - Juan Jose Arevalillo Doval (Hermes)
9. Ethics - Juan Jose Arevalillo Doval (Hermes)
 
Learn the different approaches to machine translation and how to improve the ...
Learn the different approaches to machine translation and how to improve the ...Learn the different approaches to machine translation and how to improve the ...
Learn the different approaches to machine translation and how to improve the ...
 
kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...
kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...
kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...
 
6. Entrepreneurship - Juan Jose Arevalillo Doval (Hermes)
6. Entrepreneurship - Juan Jose Arevalillo Doval (Hermes)6. Entrepreneurship - Juan Jose Arevalillo Doval (Hermes)
6. Entrepreneurship - Juan Jose Arevalillo Doval (Hermes)
 
High Volume, Rapid Turn Around Localization: Lessons Learned
High Volume, Rapid Turn Around Localization: Lessons LearnedHigh Volume, Rapid Turn Around Localization: Lessons Learned
High Volume, Rapid Turn Around Localization: Lessons Learned
 
Carla Parra Escartin - ER2 Hermes Traducciones
Carla Parra Escartin - ER2 Hermes Traducciones Carla Parra Escartin - ER2 Hermes Traducciones
Carla Parra Escartin - ER2 Hermes Traducciones
 
12. Gloria Corpas, Jorge Leiva, Miriam Seghiri (UMA) Human Translation & Tran...
12. Gloria Corpas, Jorge Leiva, Miriam Seghiri (UMA) Human Translation & Tran...12. Gloria Corpas, Jorge Leiva, Miriam Seghiri (UMA) Human Translation & Tran...
12. Gloria Corpas, Jorge Leiva, Miriam Seghiri (UMA) Human Translation & Tran...
 
Guideline for project writing
Guideline for project writingGuideline for project writing
Guideline for project writing
 
VOC real world enterprise needs
VOC real world enterprise needsVOC real world enterprise needs
VOC real world enterprise needs
 
10. Lucia Specia (USFD) Evaluation of Machine Translation
10. Lucia Specia (USFD) Evaluation of Machine Translation10. Lucia Specia (USFD) Evaluation of Machine Translation
10. Lucia Specia (USFD) Evaluation of Machine Translation
 
The I in PRIMM - Code Comprehension and Questioning
The I in PRIMM - Code Comprehension and QuestioningThe I in PRIMM - Code Comprehension and Questioning
The I in PRIMM - Code Comprehension and Questioning
 
Welocalize Throughputs and Post-Editing Productivity Webinar Laura Casanellas
Welocalize Throughputs and Post-Editing Productivity Webinar Laura CasanellasWelocalize Throughputs and Post-Editing Productivity Webinar Laura Casanellas
Welocalize Throughputs and Post-Editing Productivity Webinar Laura Casanellas
 
18. Alessandro Cattelan (Translated) Terminology
18. Alessandro Cattelan (Translated) Terminology18. Alessandro Cattelan (Translated) Terminology
18. Alessandro Cattelan (Translated) Terminology
 
DCXS best selfcare-solutions DynamicFAQ
DCXS best selfcare-solutions DynamicFAQDCXS best selfcare-solutions DynamicFAQ
DCXS best selfcare-solutions DynamicFAQ
 

Similar to Neural Machine Translation: a report from the front line

Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)TAUS - The Language Data Network
 
Is there a future for Model Transformation Languages?
Is there a future for Model Transformation Languages?Is there a future for Model Transformation Languages?
Is there a future for Model Transformation Languages?Jordi Cabot
 
KantanFest: Andy Way
KantanFest: Andy WayKantanFest: Andy Way
KantanFest: Andy Waykantanmt
 
“An Industry Standard Performance Benchmark Suite for Machine Learning,” a Pr...
“An Industry Standard Performance Benchmark Suite for Machine Learning,” a Pr...“An Industry Standard Performance Benchmark Suite for Machine Learning,” a Pr...
“An Industry Standard Performance Benchmark Suite for Machine Learning,” a Pr...Edge AI and Vision Alliance
 
Some "challenges" on the open-source/open-data front
Some "challenges" on the open-source/open-data frontSome "challenges" on the open-source/open-data front
Some "challenges" on the open-source/open-data frontGreg Landrum
 
IRJET- Applications of Artificial Intelligence in Neural Machine Translation
IRJET- Applications of Artificial Intelligence in Neural Machine TranslationIRJET- Applications of Artificial Intelligence in Neural Machine Translation
IRJET- Applications of Artificial Intelligence in Neural Machine TranslationIRJET Journal
 
Performance monitoring and call tracing in microservice environments
Performance monitoring and call tracing in microservice environmentsPerformance monitoring and call tracing in microservice environments
Performance monitoring and call tracing in microservice environmentsMartin Gutenbrunner
 
Spark meetup london share and analyse genomic data at scale with spark, adam...
Spark meetup london  share and analyse genomic data at scale with spark, adam...Spark meetup london  share and analyse genomic data at scale with spark, adam...
Spark meetup london share and analyse genomic data at scale with spark, adam...Andy Petrella
 
A comprehensive guide to prompt engineering.pdf
A comprehensive guide to prompt engineering.pdfA comprehensive guide to prompt engineering.pdf
A comprehensive guide to prompt engineering.pdfJamieDornan2
 
The Strengths & Limitations of Risk Management Standards
The Strengths & Limitations of Risk Management StandardsThe Strengths & Limitations of Risk Management Standards
The Strengths & Limitations of Risk Management StandardsBen Tomhave
 
Deep learning for text analytics
Deep learning for text analyticsDeep learning for text analytics
Deep learning for text analyticsErik Tromp
 
XP2018 presentation for Phoenix Scrum User Group 2018
XP2018 presentation for Phoenix Scrum User Group 2018XP2018 presentation for Phoenix Scrum User Group 2018
XP2018 presentation for Phoenix Scrum User Group 2018Thene Sheehy
 
(150324) Everything you ever wanted to know about Studio!
(150324) Everything you ever wanted to know about Studio!(150324) Everything you ever wanted to know about Studio!
(150324) Everything you ever wanted to know about Studio!Paul Filkin
 
5 challenges of scaling l10n workflows KantanMT/bmmt webinar
5 challenges of scaling l10n workflows KantanMT/bmmt webinar5 challenges of scaling l10n workflows KantanMT/bmmt webinar
5 challenges of scaling l10n workflows KantanMT/bmmt webinarkantanmt
 
00 Fundamentals of csharp course introduction
00 Fundamentals of csharp course introduction00 Fundamentals of csharp course introduction
00 Fundamentals of csharp course introductionmaznabili
 
Weak Supervision.pdf
Weak Supervision.pdfWeak Supervision.pdf
Weak Supervision.pdfStephenLeo7
 
Introduction to TDD
Introduction to TDDIntroduction to TDD
Introduction to TDDAhmed Misbah
 

Similar to Neural Machine Translation: a report from the front line (20)

Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
 
Is there a future for Model Transformation Languages?
Is there a future for Model Transformation Languages?Is there a future for Model Transformation Languages?
Is there a future for Model Transformation Languages?
 
KantanFest: Andy Way
KantanFest: Andy WayKantanFest: Andy Way
KantanFest: Andy Way
 
“An Industry Standard Performance Benchmark Suite for Machine Learning,” a Pr...
“An Industry Standard Performance Benchmark Suite for Machine Learning,” a Pr...“An Industry Standard Performance Benchmark Suite for Machine Learning,” a Pr...
“An Industry Standard Performance Benchmark Suite for Machine Learning,” a Pr...
 
FortranCalculus Class
FortranCalculus ClassFortranCalculus Class
FortranCalculus Class
 
Some "challenges" on the open-source/open-data front
Some "challenges" on the open-source/open-data frontSome "challenges" on the open-source/open-data front
Some "challenges" on the open-source/open-data front
 
IRJET- Applications of Artificial Intelligence in Neural Machine Translation
IRJET- Applications of Artificial Intelligence in Neural Machine TranslationIRJET- Applications of Artificial Intelligence in Neural Machine Translation
IRJET- Applications of Artificial Intelligence in Neural Machine Translation
 
Performance monitoring and call tracing in microservice environments
Performance monitoring and call tracing in microservice environmentsPerformance monitoring and call tracing in microservice environments
Performance monitoring and call tracing in microservice environments
 
Spark meetup london share and analyse genomic data at scale with spark, adam...
Spark meetup london  share and analyse genomic data at scale with spark, adam...Spark meetup london  share and analyse genomic data at scale with spark, adam...
Spark meetup london share and analyse genomic data at scale with spark, adam...
 
A comprehensive guide to prompt engineering.pdf
A comprehensive guide to prompt engineering.pdfA comprehensive guide to prompt engineering.pdf
A comprehensive guide to prompt engineering.pdf
 
FEA_basics.pdf
FEA_basics.pdfFEA_basics.pdf
FEA_basics.pdf
 
The Strengths & Limitations of Risk Management Standards
The Strengths & Limitations of Risk Management StandardsThe Strengths & Limitations of Risk Management Standards
The Strengths & Limitations of Risk Management Standards
 
Deep learning for text analytics
Deep learning for text analyticsDeep learning for text analytics
Deep learning for text analytics
 
XP2018 presentation for Phoenix Scrum User Group 2018
XP2018 presentation for Phoenix Scrum User Group 2018XP2018 presentation for Phoenix Scrum User Group 2018
XP2018 presentation for Phoenix Scrum User Group 2018
 
(150324) Everything you ever wanted to know about Studio!
(150324) Everything you ever wanted to know about Studio!(150324) Everything you ever wanted to know about Studio!
(150324) Everything you ever wanted to know about Studio!
 
5 challenges of scaling l10n workflows KantanMT/bmmt webinar
5 challenges of scaling l10n workflows KantanMT/bmmt webinar5 challenges of scaling l10n workflows KantanMT/bmmt webinar
5 challenges of scaling l10n workflows KantanMT/bmmt webinar
 
00 Fundamentals of csharp course introduction
00 Fundamentals of csharp course introduction00 Fundamentals of csharp course introduction
00 Fundamentals of csharp course introduction
 
Weak Supervision.pdf
Weak Supervision.pdfWeak Supervision.pdf
Weak Supervision.pdf
 
2019 04-23-tf lite-avid-f
2019 04-23-tf lite-avid-f2019 04-23-tf lite-avid-f
2019 04-23-tf lite-avid-f
 
Introduction to TDD
Introduction to TDDIntroduction to TDD
Introduction to TDD
 

More from Iconic Translation Machines

The growing role of translation technology in e-discovery, litigation, digita...
The growing role of translation technology in e-discovery, litigation, digita...The growing role of translation technology in e-discovery, litigation, digita...
The growing role of translation technology in e-discovery, litigation, digita...Iconic Translation Machines
 
Making the Old New Again - Modern Technical Provides Access to Historical Che...
Making the Old New Again - Modern Technical Provides Access to Historical Che...Making the Old New Again - Modern Technical Provides Access to Historical Che...
Making the Old New Again - Modern Technical Provides Access to Historical Che...Iconic Translation Machines
 
Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...Iconic Translation Machines
 
What? Why? How? Factors that impact the success of commercial MT projects
What? Why? How? Factors that impact the success of commercial MT projectsWhat? Why? How? Factors that impact the success of commercial MT projects
What? Why? How? Factors that impact the success of commercial MT projectsIconic Translation Machines
 
"Machine Translation 101" and the Challenge of Patents
"Machine Translation 101" and the Challenge of Patents"Machine Translation 101" and the Challenge of Patents
"Machine Translation 101" and the Challenge of PatentsIconic Translation Machines
 
Data and Linguistics: Delivering Machine Translation with Subject Matter Expe...
Data and Linguistics: Delivering Machine Translation with Subject Matter Expe...Data and Linguistics: Delivering Machine Translation with Subject Matter Expe...
Data and Linguistics: Delivering Machine Translation with Subject Matter Expe...Iconic Translation Machines
 
Beyond Data: Delivering Machine Translation with Subject Matter Expertise
Beyond Data: Delivering Machine Translation with Subject Matter ExpertiseBeyond Data: Delivering Machine Translation with Subject Matter Expertise
Beyond Data: Delivering Machine Translation with Subject Matter ExpertiseIconic Translation Machines
 

More from Iconic Translation Machines (10)

The growing role of translation technology in e-discovery, litigation, digita...
The growing role of translation technology in e-discovery, litigation, digita...The growing role of translation technology in e-discovery, litigation, digita...
The growing role of translation technology in e-discovery, litigation, digita...
 
Making the Old New Again - Modern Technical Provides Access to Historical Che...
Making the Old New Again - Modern Technical Provides Access to Historical Che...Making the Old New Again - Modern Technical Provides Access to Historical Che...
Making the Old New Again - Modern Technical Provides Access to Historical Che...
 
Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...
 
What? Why? How? Factors that impact the success of commercial MT projects
What? Why? How? Factors that impact the success of commercial MT projectsWhat? Why? How? Factors that impact the success of commercial MT projects
What? Why? How? Factors that impact the success of commercial MT projects
 
Machine Translation: The Neural Frontier
Machine Translation: The Neural FrontierMachine Translation: The Neural Frontier
Machine Translation: The Neural Frontier
 
Innovative Business and Pricing Models: for MT
Innovative Business and Pricing Models: for MTInnovative Business and Pricing Models: for MT
Innovative Business and Pricing Models: for MT
 
MT Evaluation: Seeing the Wood for the Trees
MT Evaluation: Seeing the Wood for the TreesMT Evaluation: Seeing the Wood for the Trees
MT Evaluation: Seeing the Wood for the Trees
 
"Machine Translation 101" and the Challenge of Patents
"Machine Translation 101" and the Challenge of Patents"Machine Translation 101" and the Challenge of Patents
"Machine Translation 101" and the Challenge of Patents
 
Data and Linguistics: Delivering Machine Translation with Subject Matter Expe...
Data and Linguistics: Delivering Machine Translation with Subject Matter Expe...Data and Linguistics: Delivering Machine Translation with Subject Matter Expe...
Data and Linguistics: Delivering Machine Translation with Subject Matter Expe...
 
Beyond Data: Delivering Machine Translation with Subject Matter Expertise
Beyond Data: Delivering Machine Translation with Subject Matter ExpertiseBeyond Data: Delivering Machine Translation with Subject Matter Expertise
Beyond Data: Delivering Machine Translation with Subject Matter Expertise
 

Recently uploaded

Church Building Grants To Assist With New Construction, Additions, And Restor...
Church Building Grants To Assist With New Construction, Additions, And Restor...Church Building Grants To Assist With New Construction, Additions, And Restor...
Church Building Grants To Assist With New Construction, Additions, And Restor...Americas Got Grants
 
Memorándum de Entendimiento (MoU) entre Codelco y SQM
Memorándum de Entendimiento (MoU) entre Codelco y SQMMemorándum de Entendimiento (MoU) entre Codelco y SQM
Memorándum de Entendimiento (MoU) entre Codelco y SQMVoces Mineras
 
TriStar Gold Corporate Presentation - April 2024
TriStar Gold Corporate Presentation - April 2024TriStar Gold Corporate Presentation - April 2024
TriStar Gold Corporate Presentation - April 2024Adnet Communications
 
Independent Call Girls Andheri Nightlaila 9967584737
Independent Call Girls Andheri Nightlaila 9967584737Independent Call Girls Andheri Nightlaila 9967584737
Independent Call Girls Andheri Nightlaila 9967584737Riya Pathan
 
Chapter 9 PPT 4th edition.pdf internal audit
Chapter 9 PPT 4th edition.pdf internal auditChapter 9 PPT 4th edition.pdf internal audit
Chapter 9 PPT 4th edition.pdf internal auditNhtLNguyn9
 
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCRashishs7044
 
Traction part 2 - EOS Model JAX Bridges.
Traction part 2 - EOS Model JAX Bridges.Traction part 2 - EOS Model JAX Bridges.
Traction part 2 - EOS Model JAX Bridges.Anamaria Contreras
 
8447779800, Low rate Call girls in Uttam Nagar Delhi NCR
8447779800, Low rate Call girls in Uttam Nagar Delhi NCR8447779800, Low rate Call girls in Uttam Nagar Delhi NCR
8447779800, Low rate Call girls in Uttam Nagar Delhi NCRashishs7044
 
Financial-Statement-Analysis-of-Coca-cola-Company.pptx
Financial-Statement-Analysis-of-Coca-cola-Company.pptxFinancial-Statement-Analysis-of-Coca-cola-Company.pptx
Financial-Statement-Analysis-of-Coca-cola-Company.pptxsaniyaimamuddin
 
Investment in The Coconut Industry by Nancy Cheruiyot
Investment in The Coconut Industry by Nancy CheruiyotInvestment in The Coconut Industry by Nancy Cheruiyot
Investment in The Coconut Industry by Nancy Cheruiyotictsugar
 
The-Ethical-issues-ghhhhhhhhjof-Byjus.pptx
The-Ethical-issues-ghhhhhhhhjof-Byjus.pptxThe-Ethical-issues-ghhhhhhhhjof-Byjus.pptx
The-Ethical-issues-ghhhhhhhhjof-Byjus.pptxmbikashkanyari
 
FULL ENJOY Call girls in Paharganj Delhi | 8377087607
FULL ENJOY Call girls in Paharganj Delhi | 8377087607FULL ENJOY Call girls in Paharganj Delhi | 8377087607
FULL ENJOY Call girls in Paharganj Delhi | 8377087607dollysharma2066
 
Innovation Conference 5th March 2024.pdf
Innovation Conference 5th March 2024.pdfInnovation Conference 5th March 2024.pdf
Innovation Conference 5th March 2024.pdfrichard876048
 
MAHA Global and IPR: Do Actions Speak Louder Than Words?
MAHA Global and IPR: Do Actions Speak Louder Than Words?MAHA Global and IPR: Do Actions Speak Louder Than Words?
MAHA Global and IPR: Do Actions Speak Louder Than Words?Olivia Kresic
 
NewBase 19 April 2024 Energy News issue - 1717 by Khaled Al Awadi.pdf
NewBase  19 April  2024  Energy News issue - 1717 by Khaled Al Awadi.pdfNewBase  19 April  2024  Energy News issue - 1717 by Khaled Al Awadi.pdf
NewBase 19 April 2024 Energy News issue - 1717 by Khaled Al Awadi.pdfKhaled Al Awadi
 
Global Scenario On Sustainable and Resilient Coconut Industry by Dr. Jelfina...
Global Scenario On Sustainable  and Resilient Coconut Industry by Dr. Jelfina...Global Scenario On Sustainable  and Resilient Coconut Industry by Dr. Jelfina...
Global Scenario On Sustainable and Resilient Coconut Industry by Dr. Jelfina...ictsugar
 
Cyber Security Training in Office Environment
Cyber Security Training in Office EnvironmentCyber Security Training in Office Environment
Cyber Security Training in Office Environmentelijahj01012
 
Youth Involvement in an Innovative Coconut Value Chain by Mwalimu Menza
Youth Involvement in an Innovative Coconut Value Chain by Mwalimu MenzaYouth Involvement in an Innovative Coconut Value Chain by Mwalimu Menza
Youth Involvement in an Innovative Coconut Value Chain by Mwalimu Menzaictsugar
 

Recently uploaded (20)

Church Building Grants To Assist With New Construction, Additions, And Restor...
Church Building Grants To Assist With New Construction, Additions, And Restor...Church Building Grants To Assist With New Construction, Additions, And Restor...
Church Building Grants To Assist With New Construction, Additions, And Restor...
 
Memorándum de Entendimiento (MoU) entre Codelco y SQM
Memorándum de Entendimiento (MoU) entre Codelco y SQMMemorándum de Entendimiento (MoU) entre Codelco y SQM
Memorándum de Entendimiento (MoU) entre Codelco y SQM
 
TriStar Gold Corporate Presentation - April 2024
TriStar Gold Corporate Presentation - April 2024TriStar Gold Corporate Presentation - April 2024
TriStar Gold Corporate Presentation - April 2024
 
Independent Call Girls Andheri Nightlaila 9967584737
Independent Call Girls Andheri Nightlaila 9967584737Independent Call Girls Andheri Nightlaila 9967584737
Independent Call Girls Andheri Nightlaila 9967584737
 
Chapter 9 PPT 4th edition.pdf internal audit
Chapter 9 PPT 4th edition.pdf internal auditChapter 9 PPT 4th edition.pdf internal audit
Chapter 9 PPT 4th edition.pdf internal audit
 
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
 
Traction part 2 - EOS Model JAX Bridges.
Traction part 2 - EOS Model JAX Bridges.Traction part 2 - EOS Model JAX Bridges.
Traction part 2 - EOS Model JAX Bridges.
 
Japan IT Week 2024 Brochure by 47Billion (English)
Japan IT Week 2024 Brochure by 47Billion (English)Japan IT Week 2024 Brochure by 47Billion (English)
Japan IT Week 2024 Brochure by 47Billion (English)
 
8447779800, Low rate Call girls in Uttam Nagar Delhi NCR
8447779800, Low rate Call girls in Uttam Nagar Delhi NCR8447779800, Low rate Call girls in Uttam Nagar Delhi NCR
8447779800, Low rate Call girls in Uttam Nagar Delhi NCR
 
Financial-Statement-Analysis-of-Coca-cola-Company.pptx
Financial-Statement-Analysis-of-Coca-cola-Company.pptxFinancial-Statement-Analysis-of-Coca-cola-Company.pptx
Financial-Statement-Analysis-of-Coca-cola-Company.pptx
 
Investment in The Coconut Industry by Nancy Cheruiyot
Investment in The Coconut Industry by Nancy CheruiyotInvestment in The Coconut Industry by Nancy Cheruiyot
Investment in The Coconut Industry by Nancy Cheruiyot
 
The-Ethical-issues-ghhhhhhhhjof-Byjus.pptx
The-Ethical-issues-ghhhhhhhhjof-Byjus.pptxThe-Ethical-issues-ghhhhhhhhjof-Byjus.pptx
The-Ethical-issues-ghhhhhhhhjof-Byjus.pptx
 
FULL ENJOY Call girls in Paharganj Delhi | 8377087607
FULL ENJOY Call girls in Paharganj Delhi | 8377087607FULL ENJOY Call girls in Paharganj Delhi | 8377087607
FULL ENJOY Call girls in Paharganj Delhi | 8377087607
 
Innovation Conference 5th March 2024.pdf
Innovation Conference 5th March 2024.pdfInnovation Conference 5th March 2024.pdf
Innovation Conference 5th March 2024.pdf
 
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCR
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCREnjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCR
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCR
 
MAHA Global and IPR: Do Actions Speak Louder Than Words?
MAHA Global and IPR: Do Actions Speak Louder Than Words?MAHA Global and IPR: Do Actions Speak Louder Than Words?
MAHA Global and IPR: Do Actions Speak Louder Than Words?
 
NewBase 19 April 2024 Energy News issue - 1717 by Khaled Al Awadi.pdf
NewBase  19 April  2024  Energy News issue - 1717 by Khaled Al Awadi.pdfNewBase  19 April  2024  Energy News issue - 1717 by Khaled Al Awadi.pdf
NewBase 19 April 2024 Energy News issue - 1717 by Khaled Al Awadi.pdf
 
Global Scenario On Sustainable and Resilient Coconut Industry by Dr. Jelfina...
Global Scenario On Sustainable  and Resilient Coconut Industry by Dr. Jelfina...Global Scenario On Sustainable  and Resilient Coconut Industry by Dr. Jelfina...
Global Scenario On Sustainable and Resilient Coconut Industry by Dr. Jelfina...
 
Cyber Security Training in Office Environment
Cyber Security Training in Office EnvironmentCyber Security Training in Office Environment
Cyber Security Training in Office Environment
 
Youth Involvement in an Innovative Coconut Value Chain by Mwalimu Menza
Youth Involvement in an Innovative Coconut Value Chain by Mwalimu MenzaYouth Involvement in an Innovative Coconut Value Chain by Mwalimu Menza
Youth Involvement in an Innovative Coconut Value Chain by Mwalimu Menza
 

Neural Machine Translation: a report from the front line

  • 1. Neural MT Separating the hype from reality a report from the front line TAUS Webinar / Industry Leaders Forum / LocWorld 34
  • 2. The Neural Narrative Great, thanks. Let me use it now…
  • 4. Impact of Neural MT Use cases covered by generic MT Use cases needing custom MTThe Bar
  • 5. Impact of Neural MT Use cases covered by generic MT Use cases needing custom MTThe Bar Neural MT has raised the bar
  • 6.
  • 7. Of course. We’re a team of MT experts. This is a big part of the value that we bring to the table. We’re not just taking open-source tools off the shelf. We’re innovating, researching, developing new processes. Same for Neural MT. e.g. lexically constrained decoding Neural MT @ Iconic “Do you ‘do’ Neural MT?”
  • 8. It’s one of the ways. MT is not a one-size-fits-all technology. What constitutes the best approach depends on the language pair, domain, use case, and various other factors. In some cases, the best approach will be Neural MT, but not yet all the time. Neural MT @ Iconic “Is this the way you do MT now?”
  • 9. When it gives the best output! When you’re customising MT, there are so many things you can do – different processors, parameters, ways of combining data and tuning. We try multiple approaches and allow our systems to use the best one. Let’s look at some case studies, but first… Neural MT @ Iconic “When do you use it then?”
  • 10. The Iconic Ensemble Architecture™
  • 11. Patents Case Study Average length: 7 words Average length: 30 words 3 languages Same data sets Client evaluation Ranking 1. Unusable 2. Poor 3. Adequate 4. Good 5. Excellent Criteria 90% Adequate or above 0% Unusable
  • 12. Linguist Review both pass title criteria only Iconic MT passed abstracts Patents Case Study – Chinese to English 31 3938 19 0 5 10 15 20 25 30 35 40 45 Titles Abstracts Iconic MT Iconic Neural MT Outcome Iconic MT deployed in production
  • 13. Linguist Review both passed on titles only NMT passed abstracts Patents Case Study – Japanese to English 52 33 0 10 20 30 40 50 60 Titles Abstracts Iconic MT Iconic Neural MT Outcome Iconic MT deployed for titles Neural MT deployed for abstracts 4 5 4 4
  • 14. Patents Case Study – Korean to English 40 25 0 5 10 15 20 25 30 35 40 45 Titles Abstracts Iconic MT Iconic Neural MT Linguist Review Iconic MT below criteria Neural MT significantly better Outcome Under review! 2 6 4 3
  • 15. Neural MT raises the bar for general purpose MT but the bar still needs to be tested. Customisation Case Study English to French English to Hindi BLEU 1-TER BLEU 1-TER Iconic MT 43.0 (+10.4) 55.2 (+7.7) 46.75 (+12.96) 56.4 (+5.5) GNMT 32.6 47.5 33.79 50.9 Iconic NMT 39.2 50.5 - - 2 languages 1.5M training segments IT content
  • 16. The Iconic Ensemble Architecture™ Neural MT is another powerful tool in our arsenal that helps us deliver best-in-class machine translation output
  • 17. “I don’t give a damn what you do!”
  • 18. MT @ Iconic – what we don’t do MT MT MT MT MT MTMT MTMTMTMTMT MTMTMTMTMTMT The ability to build your own MT engines with Moses, Phrasal, OpenNMT, Nematus, Fairseq. Provide off-the-shelf general industry engines. There are some very adequate solutions for that! MT
  • 19. Customised expert-built MT, using the most appropriate tool for the job, MT or otherwise. MT @ Iconic – what we do do! Develop products and solutions that incorporate machine translation – not just access to an API.
  • 20. Engage our expert team on an Neural MT project to see if it works for your content Neural MT – Early Adopter Program To date Custom-developments with some of our closest partners Now Inviting early adopters to expand the range of casesEarly Adopter Program

Editor's Notes

  1. Direct people to previous talks I’ve given about the impact and history of neural MT: SUMMARY it’s promising, but it’s not a one size fits all taking over approach still looking case by case in short term long term, wait and see, it’s exciting
  2. Been speaking recently about Neural MT The (commercial) narrative around neural MT is moving even faster than the pace of development! We’ve gone very quickly from explaining what it is, to companies showing initial results, to having fully blown production systems producing the best results ever – and in some cases from companies who never even offered MT before. Wow that’s impressive  Our team at Iconic know a little bit about MT but you can call me a cynic if we take the approach of still trying to manage expectations while we all learn a little more about Neural MT. Much of it’s still marketing Still needs to be contextualised This was always the case with MT, and that doesn’t change with Neural MT
  3. Short-term impact | Long-term prospects
  4. Ultimately just another type of MT so we’re still have a lot of the same issues, and some new issues Whether that custom MT is neural, or SMT, or hybrid, STILL depends. It’s still to be judged on a case by case basis
  5. Ok, so let’s talk about our approach neural MT at Iconic, but we’ll get some key question out of the way up front. Questions we're asked frequently as a provider of machine translation
  6. This is what we've been doing for many years now Fancy way of saying we can apply terminology With Moses, the way ppl do MT, a lot of this was out of the box. Now we have to implement it ourselves so that will separate the wheat from the chaff in terms of software.
  7. Beam size, phrase length, distortion limit – now training epochs, vocab size, number of hidden layers Before we talk about the HOW we do it (which is less important as I’ll point out) let’s look at what we’ve done so far with some case studies REAL RESULTS FROM THE FIELD
  8. A lot of ongoing patent work with some of our biggest clients which is an ideal starting point for us to test our production metal in this area TEST NEURAL MT ON REAL USE CASES AND CRITERIA “Baseline” Iconic MT here is
  9. WHAT: Chinese – pre-ordering system, mature 3 years, auto post-editing OUTCOME: Use Iconic where possible, because it’s quicker to retrain and more control
  10. WHAT: Japanese – syntax based pre-ordering system, transliteration and script normalisation Interesting, because we were doing A LOT of development before Neural MT but it was hard to make big improvements with constraints on data OUTCOME: Use Iconic where possible, because it’s quicker to retrain and more control in the short term
  11. Korean project Interesting, because it wasn’t something we had in production before Neural MT – mainly because it was so hard. WHAT: Korean – hierarchical system It’s a live one so the results are actually still with the client – LET’S SEE NEXT WEEK, TAUS AND LOCWORLD! Internal QA on the output suggest the automatic scores are generous to Iconic MT. The Neural output is significantly better
  12. Still ongoing. Iconic Neural MT engines in building, but this is the baseline we establish! CONCLUSIONS HERE: Customised Iconic MT is better than general neural MT for 2 very different languages Again, even customised NMT not as good So, we will use what we can where’s it’s best. NEURAL MT CUSTOMISATION NOT YET VERY POWERFUL ACROSS THE BOARD. WE’RE STARTING TO GET AN INTUITION WHERE IT WILL HELP AND NOT.
  13. Where does NEURAL FIT IN? HOWEVER, it’s all well and good looking being the curtain and how we do this but at the end of the day, a particular quote springs to mind….
  14. This was a quote from a prospective client on a call last month. I was in the midst of explain what we use in which cases, where neural MT fits in, and they interrupted me as said “I don’t give a damn what you use”. I thought for a second as I was disrupted from my flow and thought, he’s right you know. I’m telling people to leave it to us, and that’s what he wants. Why does it matter how the translations are produced? Does it really matter if it’s neural or not – once it’s guaranteed as the best of what we could achieve, including using neural. I don’t think it does to anyone! But because you’ve decided to watch, I’ll give you some insight into what we do and don’t do
  15. - With SMT/NMT, whatever, this it will get you so far before more expertise is required. This is the case now more than ever with NMT and how experimental it is. - Not trying to provide off the shelf generic engines. Never done that. That’s the realm of Google. You’ll find it’s quite good for the general use case! Good basis for customisation.
  16. We’re doing what we’ve always done! EDISCOVERY REGULATORY COMPLIANCE WHERE MT IS A PART OF A BROADER SOLUTION
  17. To close the loop on this story with Iconic and NEURAL MT We’re learning, fast, and the more REAL opportunities there are the better for everyone. Let us know if you have any questions or if it’s something you’d like to explore. THANKS!