SlideShare uma empresa Scribd logo
1 de 15
Baixar para ler offline
Beyond the Hype
of Neural Machine
Translation
Tauyou & Prompsit
(Diego) dbc@tauyou.com | (Gema) gramirez@prompsit.com
Why neural nets?
“artificial neural networks [...] are able to be trained
from examples without the need for a thorough
understanding of the task in hand, and able to show
surprising generalization performance and predicting
power”
Mikel L. Forcada (Neural Networks: Automata and Formal Models of Computation)
Why neural nets in MT now?
MT maturity
➔ MT is widely used (but planning to use it everywhere)
➔ MT for some languages is still not good enough (yes for others)
➔ RBMT, SMT and hybrid MT approaches widely exploited
Resources availability
➔ Computational power available and cheap (GPUs)
➔ Deep learning algorithms and frameworks available
➔ Data to learn from also available (corpora)
So, why not?
Promising results from WMT16 competition: all best systems are NMT ones
SMT NMT
BLEU TER BLEU TER
en-fi* 14.8 0.76 17.8 0.72
en-ro 27.4 0.61 28.7 0.60
en-ru 24.0 0.68 26.0 0.65
en-de 31.4 0.58 34.8 0.54
en-cz 24.1 0.67 26.3 0.63
* en-fi are Prompsit’s + DCU systems
Neural nets are...
➔ ...computational models inspired by Biology
➔ ...playing increasing key roles in Graphics and Pattern Recognition
➔ ...experiencing a new edge thanks to hardware and deep learning
➔ ...made of encoding/decoding ‘neurons’
➔ ...applied to translation (= neural MT = NMT):
◆ encode SL words as vectors that represent the relevant
information
◆ decode vectors into words preserving syntactic and semantic
information in the TL
NMT requires...
➔ Hardware: raw 10xCPUs or GPU
(times get shorter with GPUs)
➔ Software: deep learning framework
(Theano, Torch, etc.) + NMT libraries
➔ Data: bilingual corpora
(monolingual for LM only)
➔ Learning & (early) stopping: iteratively, translation models are created.
➔ Picking up a model: evaluation and selection of best model(s)
➔ Translating: model(s) are used to translate
Down to the NMT
business
Applying NMT to generic and in-domain use cases
Generic English -- Swedish SMT vs. NMT
➔ Same generic corpus (8M segments), same training and test sets
➔ SMT: Moses-based with no tuning on CPU
➔ NMT: Theano-based Groundhog NMT toolkit on GPU
Domain-specific English -- Norwegian SMT vs. NMT
➔ Same in-domain corpus (800K segments), same training and test sets
➔ SMT: Moses-based + tuning on CPU
➔ NMT: Theano-based Groundhog NMT toolkit on GPU
Comparison for generic English - Swedish
SMT NMT
Training time 48 hours (CPU) 2 weeks (GPU)
Translation time 00:12:35 (866 segments) 01:38:47 (866 segments)
CPU usage in translation 56% (CPU) 100% (CPU)
Space in disk 37.7 GB 9.1GB
BLEU score 0.440 0.404
Identical matches 19.33% (161/866) 12% (104/866)
Edit distance similarity 0.78 0.746
Comparison for in-domain English - Norwegian
SMT NMT
Training time 1.8 hours (3 CPUs) 7 days (1 GPU)
Translation time 00:01:22 (1,000 segments) 02:08:00 (1,000 segments)
CPU usage in translation 56% (CPU) 100% (CPU)
Space in disk 2.3 GB 6.5GB
BLEU score 0.53 0.62
Identical matches 27.76% (276/1000) 30% (300/1000)
Edit distance similarity 0.77 0.83
Conclusions SMT vs. NMT: technical insight
SMT NMT
Space in disk ✘ ✓ Smaller
CPU during translation ✓ ✘
RAM during translation ✘ ✓ Lesser
Training speed rate ✓ Faster ✘ Can be optimized by hardware
Translation speed rate ✓ Faster ✘ Can be optimized by hardware
In domain
SMT NMT
BLEU ✘ ✓
Identical matches ✘ ✓
Edit distance similarity ✘ ✓
Translators feedback ✓ ✘
Generic
SMT NMT
BLEU ≈ ≈
Identical matches ✓ ✘
Edit distance similarity ≈ ≈
Translators feedback ✓ ✘
Conclusions SMT vs. NMT: qualitative insight
Final conclusions
➔ NMT is a new big player in MT:
◆ Research now focusing heavily on NMT: already
outperforms SMT in many cases
◆ Use case results: with little effort, it is on par with SMT
◆ Hardware requirements are more demanding for NMT:
higher budget
◆ Translators feedback: SMT is still better
Final conclusions
➔ SMT, and other approaches, more robust and alive
◆ Better quality and consistency in MT output.
◆ Better ROI, specially for real-time translation applications
where speed is critical
➔ Deep learning for other NLP applications?
◆ Of course! Vivid in quality estimation, terminology,
sentiment analysis, etc.
Thanks!
Go raibh maith agaibh!
Tauyou & Prompsit
(Diego) dbc@tauyou.com | (Gema) gramirez@prompsit.com

Mais conteĂșdo relacionado

Mais de tauyou

APIfying the Translation Industry
APIfying the Translation IndustryAPIfying the Translation Industry
APIfying the Translation Industrytauyou
 
The Discreet Charm of Machine Translation
The Discreet Charm of Machine TranslationThe Discreet Charm of Machine Translation
The Discreet Charm of Machine Translationtauyou
 
Women in Localization UK Webinar with Diego Bartolome
Women in Localization UK Webinar with Diego BartolomeWomen in Localization UK Webinar with Diego Bartolome
Women in Localization UK Webinar with Diego Bartolometauyou
 
TAUS Post-editing webinar. Spanish-to-English Module
TAUS Post-editing webinar. Spanish-to-English ModuleTAUS Post-editing webinar. Spanish-to-English Module
TAUS Post-editing webinar. Spanish-to-English Moduletauyou
 
The Beauty of Machine Translation
The Beauty of Machine TranslationThe Beauty of Machine Translation
The Beauty of Machine Translationtauyou
 
Emerging Technologies Enabling New Business Models
Emerging Technologies Enabling New Business ModelsEmerging Technologies Enabling New Business Models
Emerging Technologies Enabling New Business Modelstauyou
 
Innovating in Translation
Innovating in TranslationInnovating in Translation
Innovating in Translationtauyou
 
Pushing Machine Translation Forward
Pushing Machine Translation ForwardPushing Machine Translation Forward
Pushing Machine Translation Forwardtauyou
 
The State of Post-Editing
The State of Post-EditingThe State of Post-Editing
The State of Post-Editingtauyou
 
Machine Translation Master Class at the EUATC Conference by Diego Bartolome
Machine Translation Master Class at the EUATC Conference by Diego BartolomeMachine Translation Master Class at the EUATC Conference by Diego Bartolome
Machine Translation Master Class at the EUATC Conference by Diego Bartolometauyou
 
lo que he aprendido (y quiero compartir)
lo que he aprendido (y quiero compartir)lo que he aprendido (y quiero compartir)
lo que he aprendido (y quiero compartir)tauyou
 
What you need to put Machine Translation into practice: Tools, People, and Pr...
What you need to put Machine Translation into practice: Tools, People, and Pr...What you need to put Machine Translation into practice: Tools, People, and Pr...
What you need to put Machine Translation into practice: Tools, People, and Pr...tauyou
 
How we failed to win a 100,000,000 word contract (GALA Istanbul 2014)
How we failed to win a 100,000,000 word contract (GALA Istanbul 2014)How we failed to win a 100,000,000 word contract (GALA Istanbul 2014)
How we failed to win a 100,000,000 word contract (GALA Istanbul 2014)tauyou
 
Learn to Innovate (GALA Istanbul 2014)
Learn to Innovate (GALA Istanbul 2014)Learn to Innovate (GALA Istanbul 2014)
Learn to Innovate (GALA Istanbul 2014)tauyou
 
Entrepreneurship in Education
Entrepreneurship in EducationEntrepreneurship in Education
Entrepreneurship in Educationtauyou
 
2013 UAB Barcelona: Change the world (one start-up at a time)
2013 UAB Barcelona: Change the world (one start-up at a time)2013 UAB Barcelona: Change the world (one start-up at a time)
2013 UAB Barcelona: Change the world (one start-up at a time)tauyou
 
2013 Tekom Wiesbaden: A Business Model Generation Session
2013 Tekom Wiesbaden: A Business Model Generation Session2013 Tekom Wiesbaden: A Business Model Generation Session
2013 Tekom Wiesbaden: A Business Model Generation Sessiontauyou
 
2013 ATC Conference London: New Business Models for the Translation Industry
2013 ATC Conference London: New Business Models for the Translation Industry2013 ATC Conference London: New Business Models for the Translation Industry
2013 ATC Conference London: New Business Models for the Translation Industrytauyou
 
2013 TMS Inspiration Days Krakow: A Business Model Generation Session
2013 TMS Inspiration Days Krakow: A Business Model Generation Session2013 TMS Inspiration Days Krakow: A Business Model Generation Session
2013 TMS Inspiration Days Krakow: A Business Model Generation Sessiontauyou
 
2013 GALA Miami: Breaking into Latin Maerican Markets on a Small Budget
2013 GALA Miami: Breaking into Latin Maerican Markets on a Small Budget2013 GALA Miami: Breaking into Latin Maerican Markets on a Small Budget
2013 GALA Miami: Breaking into Latin Maerican Markets on a Small Budgettauyou
 

Mais de tauyou (20)

APIfying the Translation Industry
APIfying the Translation IndustryAPIfying the Translation Industry
APIfying the Translation Industry
 
The Discreet Charm of Machine Translation
The Discreet Charm of Machine TranslationThe Discreet Charm of Machine Translation
The Discreet Charm of Machine Translation
 
Women in Localization UK Webinar with Diego Bartolome
Women in Localization UK Webinar with Diego BartolomeWomen in Localization UK Webinar with Diego Bartolome
Women in Localization UK Webinar with Diego Bartolome
 
TAUS Post-editing webinar. Spanish-to-English Module
TAUS Post-editing webinar. Spanish-to-English ModuleTAUS Post-editing webinar. Spanish-to-English Module
TAUS Post-editing webinar. Spanish-to-English Module
 
The Beauty of Machine Translation
The Beauty of Machine TranslationThe Beauty of Machine Translation
The Beauty of Machine Translation
 
Emerging Technologies Enabling New Business Models
Emerging Technologies Enabling New Business ModelsEmerging Technologies Enabling New Business Models
Emerging Technologies Enabling New Business Models
 
Innovating in Translation
Innovating in TranslationInnovating in Translation
Innovating in Translation
 
Pushing Machine Translation Forward
Pushing Machine Translation ForwardPushing Machine Translation Forward
Pushing Machine Translation Forward
 
The State of Post-Editing
The State of Post-EditingThe State of Post-Editing
The State of Post-Editing
 
Machine Translation Master Class at the EUATC Conference by Diego Bartolome
Machine Translation Master Class at the EUATC Conference by Diego BartolomeMachine Translation Master Class at the EUATC Conference by Diego Bartolome
Machine Translation Master Class at the EUATC Conference by Diego Bartolome
 
lo que he aprendido (y quiero compartir)
lo que he aprendido (y quiero compartir)lo que he aprendido (y quiero compartir)
lo que he aprendido (y quiero compartir)
 
What you need to put Machine Translation into practice: Tools, People, and Pr...
What you need to put Machine Translation into practice: Tools, People, and Pr...What you need to put Machine Translation into practice: Tools, People, and Pr...
What you need to put Machine Translation into practice: Tools, People, and Pr...
 
How we failed to win a 100,000,000 word contract (GALA Istanbul 2014)
How we failed to win a 100,000,000 word contract (GALA Istanbul 2014)How we failed to win a 100,000,000 word contract (GALA Istanbul 2014)
How we failed to win a 100,000,000 word contract (GALA Istanbul 2014)
 
Learn to Innovate (GALA Istanbul 2014)
Learn to Innovate (GALA Istanbul 2014)Learn to Innovate (GALA Istanbul 2014)
Learn to Innovate (GALA Istanbul 2014)
 
Entrepreneurship in Education
Entrepreneurship in EducationEntrepreneurship in Education
Entrepreneurship in Education
 
2013 UAB Barcelona: Change the world (one start-up at a time)
2013 UAB Barcelona: Change the world (one start-up at a time)2013 UAB Barcelona: Change the world (one start-up at a time)
2013 UAB Barcelona: Change the world (one start-up at a time)
 
2013 Tekom Wiesbaden: A Business Model Generation Session
2013 Tekom Wiesbaden: A Business Model Generation Session2013 Tekom Wiesbaden: A Business Model Generation Session
2013 Tekom Wiesbaden: A Business Model Generation Session
 
2013 ATC Conference London: New Business Models for the Translation Industry
2013 ATC Conference London: New Business Models for the Translation Industry2013 ATC Conference London: New Business Models for the Translation Industry
2013 ATC Conference London: New Business Models for the Translation Industry
 
2013 TMS Inspiration Days Krakow: A Business Model Generation Session
2013 TMS Inspiration Days Krakow: A Business Model Generation Session2013 TMS Inspiration Days Krakow: A Business Model Generation Session
2013 TMS Inspiration Days Krakow: A Business Model Generation Session
 
2013 GALA Miami: Breaking into Latin Maerican Markets on a Small Budget
2013 GALA Miami: Breaking into Latin Maerican Markets on a Small Budget2013 GALA Miami: Breaking into Latin Maerican Markets on a Small Budget
2013 GALA Miami: Breaking into Latin Maerican Markets on a Small Budget
 

Último

EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...gurkirankumar98700
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsRoshan Dwivedi
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 

Último (20)

EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍾 8923113531 🎰 Avail...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 

Beyond the Hype of Neural Machine Translation

  • 1. Beyond the Hype of Neural Machine Translation Tauyou & Prompsit (Diego) dbc@tauyou.com | (Gema) gramirez@prompsit.com
  • 2. Why neural nets? “artificial neural networks [...] are able to be trained from examples without the need for a thorough understanding of the task in hand, and able to show surprising generalization performance and predicting power” Mikel L. Forcada (Neural Networks: Automata and Formal Models of Computation)
  • 3. Why neural nets in MT now? MT maturity ➔ MT is widely used (but planning to use it everywhere) ➔ MT for some languages is still not good enough (yes for others) ➔ RBMT, SMT and hybrid MT approaches widely exploited Resources availability ➔ Computational power available and cheap (GPUs) ➔ Deep learning algorithms and frameworks available ➔ Data to learn from also available (corpora)
  • 4. So, why not? Promising results from WMT16 competition: all best systems are NMT ones SMT NMT BLEU TER BLEU TER en-fi* 14.8 0.76 17.8 0.72 en-ro 27.4 0.61 28.7 0.60 en-ru 24.0 0.68 26.0 0.65 en-de 31.4 0.58 34.8 0.54 en-cz 24.1 0.67 26.3 0.63 * en-fi are Prompsit’s + DCU systems
  • 5. Neural nets are... ➔ ...computational models inspired by Biology ➔ ...playing increasing key roles in Graphics and Pattern Recognition ➔ ...experiencing a new edge thanks to hardware and deep learning ➔ ...made of encoding/decoding ‘neurons’ ➔ ...applied to translation (= neural MT = NMT): ◆ encode SL words as vectors that represent the relevant information ◆ decode vectors into words preserving syntactic and semantic information in the TL
  • 6. NMT requires... ➔ Hardware: raw 10xCPUs or GPU (times get shorter with GPUs) ➔ Software: deep learning framework (Theano, Torch, etc.) + NMT libraries ➔ Data: bilingual corpora (monolingual for LM only) ➔ Learning & (early) stopping: iteratively, translation models are created. ➔ Picking up a model: evaluation and selection of best model(s) ➔ Translating: model(s) are used to translate
  • 7. Down to the NMT business
  • 8. Applying NMT to generic and in-domain use cases Generic English -- Swedish SMT vs. NMT ➔ Same generic corpus (8M segments), same training and test sets ➔ SMT: Moses-based with no tuning on CPU ➔ NMT: Theano-based Groundhog NMT toolkit on GPU Domain-specific English -- Norwegian SMT vs. NMT ➔ Same in-domain corpus (800K segments), same training and test sets ➔ SMT: Moses-based + tuning on CPU ➔ NMT: Theano-based Groundhog NMT toolkit on GPU
  • 9. Comparison for generic English - Swedish SMT NMT Training time 48 hours (CPU) 2 weeks (GPU) Translation time 00:12:35 (866 segments) 01:38:47 (866 segments) CPU usage in translation 56% (CPU) 100% (CPU) Space in disk 37.7 GB 9.1GB BLEU score 0.440 0.404 Identical matches 19.33% (161/866) 12% (104/866) Edit distance similarity 0.78 0.746
  • 10. Comparison for in-domain English - Norwegian SMT NMT Training time 1.8 hours (3 CPUs) 7 days (1 GPU) Translation time 00:01:22 (1,000 segments) 02:08:00 (1,000 segments) CPU usage in translation 56% (CPU) 100% (CPU) Space in disk 2.3 GB 6.5GB BLEU score 0.53 0.62 Identical matches 27.76% (276/1000) 30% (300/1000) Edit distance similarity 0.77 0.83
  • 11. Conclusions SMT vs. NMT: technical insight SMT NMT Space in disk ✘ ✓ Smaller CPU during translation ✓ ✘ RAM during translation ✘ ✓ Lesser Training speed rate ✓ Faster ✘ Can be optimized by hardware Translation speed rate ✓ Faster ✘ Can be optimized by hardware
  • 12. In domain SMT NMT BLEU ✘ ✓ Identical matches ✘ ✓ Edit distance similarity ✘ ✓ Translators feedback ✓ ✘ Generic SMT NMT BLEU ≈ ≈ Identical matches ✓ ✘ Edit distance similarity ≈ ≈ Translators feedback ✓ ✘ Conclusions SMT vs. NMT: qualitative insight
  • 13. Final conclusions ➔ NMT is a new big player in MT: ◆ Research now focusing heavily on NMT: already outperforms SMT in many cases ◆ Use case results: with little effort, it is on par with SMT ◆ Hardware requirements are more demanding for NMT: higher budget ◆ Translators feedback: SMT is still better
  • 14. Final conclusions ➔ SMT, and other approaches, more robust and alive ◆ Better quality and consistency in MT output. ◆ Better ROI, specially for real-time translation applications where speed is critical ➔ Deep learning for other NLP applications? ◆ Of course! Vivid in quality estimation, terminology, sentiment analysis, etc.
  • 15. Thanks! Go raibh maith agaibh! Tauyou & Prompsit (Diego) dbc@tauyou.com | (Gema) gramirez@prompsit.com