SlideShare a Scribd company logo
1 of 26
Download to read offline
Neural MachineTranslation
A brief introduction
2016
Jose Luis Bonilla Sánchez, eBay MTLS Manager
Some Context
Machine Learning Intro
Refresher on MT History
Neural MT
NMT vs SMT
WHAT IS NEURAL MACHINE TRANSLATION?
Neural MT = A particular application of Neural Networks
Neural
Networks
MT
Self-Driving
Cars
Etc.
Script
Recognition
Price
Prediction
So what are Neural Networks?
Neural Networks
Decision Trees
Linear Regressions
Knowledge
Representation
Machine Learning
Evolutionary
Computation
EM Algorithms,
etc.
Fuzzy Systems,
etc.
Some Definitions
AI: A branch of computer science dealing with the
simulation of intelligent behavior in computers.
Machine Learning:
A type of AI that provides computers with the ability
to learn without being explicitly programmed.
Neural Networks: A ML data approach consisting of a
large number of simple, high-interconnected processing
elements (artificial neurons) in an architecture inspired by
the structure of the cerebral cortex of the brain.
Quick Machine Learning Intro
There are Many Types of ML…
ML Algorithm mind map from http://machinelearningmastery.com/
…But they all have the Same Principles
From “Machine Learning with Apache Spark”, by David Taieb
The Machine Learning Flow
…And They Deliver Great Results
Deep Learning (ML’s newest wave) can detect patterns and make
predictions at a vastly deeper level than old-fashioned statistics
Example:
Deep Learning
vs
Traditional
Statistics
If ML is so great, why do we only hear about it now?
- Increased computational power (GPUs, TPUs)
- Flood of available data
- Better algorithms
- Private companies embracing it
….and open-sourcing their tools
So… Machine Learning is Everywhere
News Summarization
Speech
Understanding
Face Recognition
Fraud Detection
Price Prediction
Machine Translation
Drug
Development
Spam Filtering
Buyer
Recommendations
Product Demand Forecast
Self-Driving Cars
Chatbots
AQuick Refresher on MT History
Rules-based
Types of Machine Translation Systems
Statistical Neural
Rule-Based Machine Translation (RBMT) – 1970s-2000s
The linguistic approach: mapping one language to another through
rules and dictionaries.
Source
Text
Translation
Lexicographic
Analysis
Syntactic
Analysis
Morphological
Analysis
Target
Text
Statistical Machine Translation (SMT) 1990s-Today
Forget linguistics – let’s look for statistical
patterns in bilingual texts. Data
Translation
(search for best
possible
translation)
Text
(input)
Text
(output)
Language
Model
Translation
Model
Training
How?
SMT – Translation Model – the “Translator”
Translation rules are learnt by finding patterns in parallel text documents
These rules are used to translate new texts (“crack the code”)
car
car
English text
Auto
Auto
German text
Mein Auto ist rot.
My car is red.
decode
car
Wagen
src -> trg | prob
car -> Auto | 0.9
car -> Wagen | 0.1
SMT– Language Model – the “Proofreader”
The Translation Model’s results are “tuned” by the Language Model to produce
more fluent sentences
My car is red.
English text
My car drives fast
You drive my car
I drive my car
N-gram count
my 4
car 4
is 1
… …
my car 4
… …
drive my car 2
… …
Neural MachineTranslation
BASIC STRUCTURE
Source words are
converted to numbers
and added up (encoded)
to produce a final score
for the whole sentence,
which is then decoded
to the target
2 Parts:
Encoder and Decoder
A PRACTICAL EXAMPLE
The new Google NMT at work
NMT GOES BEYOND N-GRAMS
Recurrent
structure in NMT
keeps track of long
dependencies (as
opposed to SMT's
n-grams)
THE LOGIC BEHIND
1
1
0.5
0.9
1.3
INPUT
LAYER
HIDDEN
LAYER
OUTPUT
LAYER
weights
activation
function
0.79
0.4
0
weights
0.8
0.2
0.3
0.9
0.5
1
0.73
0.8
0.69
Difference SMT - NMT
SMT is a White Box technology NMT is Black Box
Translation Model
Language Model
Alignment
If you look inside you will only see numbers
(matrixes/word embeddings)
Others
NEURAL MACHINE TRANSLATION (2015-…)
…Just a sea of numbers scientists cannot manipulate. If it doesn’t work, they have these choices:
Change the NN:
- Hyper-parameters
- Topology (# of
nodes and layers)
- Architecture
Re-train to focus on a domain:
Replacing the
training data
Continuing
with a subset
of the training
data
Does this change linguists’ work?
Essentially: Remember the Machine Learning workflow?
The Machine Learning Flow – Always
No.
NMT vs SMT: Performance Comparison
Neural MT vs SMT
Handling complex (Chinese) or
morphologically rich (Russian) languages
NMT better
Word reordering NMT better
Fluency NMT better
Adequacy NMT may give problems (more deviations that
make sense, rare words, whole information
bits missing)
Volume of training data needed Generally, NMT needs more data, but this
depends on processing capacity
Unpredictable errors More likely (specially if insufficient training
data)

More Related Content

Similar to Neural Machine Translation Intro

Getting Started with Machine Learning.Net & Windows Machine Learning
Getting Started with Machine Learning.Net & Windows Machine LearningGetting Started with Machine Learning.Net & Windows Machine Learning
Getting Started with Machine Learning.Net & Windows Machine LearningBruno Capuano
 
Beyond Post-Editing: The Work of the eBay MTLS
Beyond Post-Editing: The Work of the eBay MTLSBeyond Post-Editing: The Work of the eBay MTLS
Beyond Post-Editing: The Work of the eBay MTLSJose Luis Bonilla Sánchez
 
Beyond Post-Editing - How the eBay MTLS Reinvent the Linguist´s Role
Beyond Post-Editing - How the eBay MTLS Reinvent the Linguist´s RoleBeyond Post-Editing - How the eBay MTLS Reinvent the Linguist´s Role
Beyond Post-Editing - How the eBay MTLS Reinvent the Linguist´s RoleJose Luis Bonilla Sánchez
 
201909 Automated ML for Developers
201909 Automated ML for Developers201909 Automated ML for Developers
201909 Automated ML for DevelopersMark Tabladillo
 
Neural Machine Translation and power of machine translation.pptx
Neural Machine Translation and power of machine translation.pptxNeural Machine Translation and power of machine translation.pptx
Neural Machine Translation and power of machine translation.pptx2023000674ibrahim
 
Webinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Webinar GLUGNet - Machine Learning.Net and Windows Machine LearningWebinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Webinar GLUGNet - Machine Learning.Net and Windows Machine LearningBruno Capuano
 
Basic terms used in microprocessor
Basic terms used in microprocessorBasic terms used in microprocessor
Basic terms used in microprocessorRamaPrabha24
 
2018 12 18 Tech Valley UserGroup Machine Learning.Net
2018 12 18 Tech Valley UserGroup Machine Learning.Net2018 12 18 Tech Valley UserGroup Machine Learning.Net
2018 12 18 Tech Valley UserGroup Machine Learning.NetBruno Capuano
 
Artificial intelligence slides beginners
Artificial intelligence slides beginners Artificial intelligence slides beginners
Artificial intelligence slides beginners Antonio Fernandes
 
number system understand
number system  understandnumber system  understand
number system understandrickypatel151
 
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
 
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Codemotion
 
NLP Techniques for Text Generation.docx
NLP Techniques for Text Generation.docxNLP Techniques for Text Generation.docx
NLP Techniques for Text Generation.docxKevinSims18
 
Assembly chapter One.pptx
Assembly chapter One.pptxAssembly chapter One.pptx
Assembly chapter One.pptxssuserb78e291
 
Deep Learning for Machine Translation: a paradigm shift - Alberto Massidda - ...
Deep Learning for Machine Translation: a paradigm shift - Alberto Massidda - ...Deep Learning for Machine Translation: a paradigm shift - Alberto Massidda - ...
Deep Learning for Machine Translation: a paradigm shift - Alberto Massidda - ...Codemotion
 
Assembly Language In Electronics
Assembly Language In ElectronicsAssembly Language In Electronics
Assembly Language In ElectronicsAsaduzzaman Kanok
 

Similar to Neural Machine Translation Intro (20)

Getting Started with Machine Learning.Net & Windows Machine Learning
Getting Started with Machine Learning.Net & Windows Machine LearningGetting Started with Machine Learning.Net & Windows Machine Learning
Getting Started with Machine Learning.Net & Windows Machine Learning
 
Moses
MosesMoses
Moses
 
Beyond Post-Editing: The Work of the eBay MTLS
Beyond Post-Editing: The Work of the eBay MTLSBeyond Post-Editing: The Work of the eBay MTLS
Beyond Post-Editing: The Work of the eBay MTLS
 
Beyond Post-Editing - How the eBay MTLS Reinvent the Linguist´s Role
Beyond Post-Editing - How the eBay MTLS Reinvent the Linguist´s RoleBeyond Post-Editing - How the eBay MTLS Reinvent the Linguist´s Role
Beyond Post-Editing - How the eBay MTLS Reinvent the Linguist´s Role
 
Introduction to ML.NET
Introduction to ML.NETIntroduction to ML.NET
Introduction to ML.NET
 
201909 Automated ML for Developers
201909 Automated ML for Developers201909 Automated ML for Developers
201909 Automated ML for Developers
 
Neural Machine Translation and power of machine translation.pptx
Neural Machine Translation and power of machine translation.pptxNeural Machine Translation and power of machine translation.pptx
Neural Machine Translation and power of machine translation.pptx
 
Ntroduction to computer architecture and organization
Ntroduction to computer architecture and organizationNtroduction to computer architecture and organization
Ntroduction to computer architecture and organization
 
Webinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Webinar GLUGNet - Machine Learning.Net and Windows Machine LearningWebinar GLUGNet - Machine Learning.Net and Windows Machine Learning
Webinar GLUGNet - Machine Learning.Net and Windows Machine Learning
 
Basic terms used in microprocessor
Basic terms used in microprocessorBasic terms used in microprocessor
Basic terms used in microprocessor
 
2018 12 18 Tech Valley UserGroup Machine Learning.Net
2018 12 18 Tech Valley UserGroup Machine Learning.Net2018 12 18 Tech Valley UserGroup Machine Learning.Net
2018 12 18 Tech Valley UserGroup Machine Learning.Net
 
Artificial intelligence slides beginners
Artificial intelligence slides beginners Artificial intelligence slides beginners
Artificial intelligence slides beginners
 
number system understand
number system  understandnumber system  understand
number system understand
 
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
 
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...
 
NLP Techniques for Text Generation.docx
NLP Techniques for Text Generation.docxNLP Techniques for Text Generation.docx
NLP Techniques for Text Generation.docx
 
Par com
Par comPar com
Par com
 
Assembly chapter One.pptx
Assembly chapter One.pptxAssembly chapter One.pptx
Assembly chapter One.pptx
 
Deep Learning for Machine Translation: a paradigm shift - Alberto Massidda - ...
Deep Learning for Machine Translation: a paradigm shift - Alberto Massidda - ...Deep Learning for Machine Translation: a paradigm shift - Alberto Massidda - ...
Deep Learning for Machine Translation: a paradigm shift - Alberto Massidda - ...
 
Assembly Language In Electronics
Assembly Language In ElectronicsAssembly Language In Electronics
Assembly Language In Electronics
 

Recently uploaded

ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...apidays
 
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...apidays
 
A Beginners Guide to Building a RAG App Using Open Source Milvus
A Beginners Guide to Building a RAG App Using Open Source MilvusA Beginners Guide to Building a RAG App Using Open Source Milvus
A Beginners Guide to Building a RAG App Using Open Source MilvusZilliz
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
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
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024The Digital Insurer
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
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
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 

Recently uploaded (20)

ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
 
A Beginners Guide to Building a RAG App Using Open Source Milvus
A Beginners Guide to Building a RAG App Using Open Source MilvusA Beginners Guide to Building a RAG App Using Open Source Milvus
A Beginners Guide to Building a RAG App Using Open Source Milvus
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
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
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
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
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 

Neural Machine Translation Intro

  • 1. Neural MachineTranslation A brief introduction 2016 Jose Luis Bonilla Sánchez, eBay MTLS Manager
  • 2. Some Context Machine Learning Intro Refresher on MT History Neural MT NMT vs SMT
  • 3. WHAT IS NEURAL MACHINE TRANSLATION? Neural MT = A particular application of Neural Networks Neural Networks MT Self-Driving Cars Etc. Script Recognition Price Prediction
  • 4. So what are Neural Networks? Neural Networks Decision Trees Linear Regressions Knowledge Representation Machine Learning Evolutionary Computation EM Algorithms, etc. Fuzzy Systems, etc.
  • 5. Some Definitions AI: A branch of computer science dealing with the simulation of intelligent behavior in computers. Machine Learning: A type of AI that provides computers with the ability to learn without being explicitly programmed. Neural Networks: A ML data approach consisting of a large number of simple, high-interconnected processing elements (artificial neurons) in an architecture inspired by the structure of the cerebral cortex of the brain.
  • 7. There are Many Types of ML… ML Algorithm mind map from http://machinelearningmastery.com/
  • 8. …But they all have the Same Principles From “Machine Learning with Apache Spark”, by David Taieb The Machine Learning Flow
  • 9. …And They Deliver Great Results Deep Learning (ML’s newest wave) can detect patterns and make predictions at a vastly deeper level than old-fashioned statistics Example: Deep Learning vs Traditional Statistics
  • 10. If ML is so great, why do we only hear about it now? - Increased computational power (GPUs, TPUs) - Flood of available data - Better algorithms - Private companies embracing it ….and open-sourcing their tools
  • 11. So… Machine Learning is Everywhere News Summarization Speech Understanding Face Recognition Fraud Detection Price Prediction Machine Translation Drug Development Spam Filtering Buyer Recommendations Product Demand Forecast Self-Driving Cars Chatbots
  • 12. AQuick Refresher on MT History
  • 13. Rules-based Types of Machine Translation Systems Statistical Neural
  • 14. Rule-Based Machine Translation (RBMT) – 1970s-2000s The linguistic approach: mapping one language to another through rules and dictionaries. Source Text Translation Lexicographic Analysis Syntactic Analysis Morphological Analysis Target Text
  • 15. Statistical Machine Translation (SMT) 1990s-Today Forget linguistics – let’s look for statistical patterns in bilingual texts. Data Translation (search for best possible translation) Text (input) Text (output) Language Model Translation Model Training How?
  • 16. SMT – Translation Model – the “Translator” Translation rules are learnt by finding patterns in parallel text documents These rules are used to translate new texts (“crack the code”) car car English text Auto Auto German text Mein Auto ist rot. My car is red. decode car Wagen src -> trg | prob car -> Auto | 0.9 car -> Wagen | 0.1
  • 17. SMT– Language Model – the “Proofreader” The Translation Model’s results are “tuned” by the Language Model to produce more fluent sentences My car is red. English text My car drives fast You drive my car I drive my car N-gram count my 4 car 4 is 1 … … my car 4 … … drive my car 2 … …
  • 19. BASIC STRUCTURE Source words are converted to numbers and added up (encoded) to produce a final score for the whole sentence, which is then decoded to the target 2 Parts: Encoder and Decoder
  • 20. A PRACTICAL EXAMPLE The new Google NMT at work
  • 21. NMT GOES BEYOND N-GRAMS Recurrent structure in NMT keeps track of long dependencies (as opposed to SMT's n-grams)
  • 23. Difference SMT - NMT SMT is a White Box technology NMT is Black Box Translation Model Language Model Alignment If you look inside you will only see numbers (matrixes/word embeddings) Others
  • 24. NEURAL MACHINE TRANSLATION (2015-…) …Just a sea of numbers scientists cannot manipulate. If it doesn’t work, they have these choices: Change the NN: - Hyper-parameters - Topology (# of nodes and layers) - Architecture Re-train to focus on a domain: Replacing the training data Continuing with a subset of the training data
  • 25. Does this change linguists’ work? Essentially: Remember the Machine Learning workflow? The Machine Learning Flow – Always No.
  • 26. NMT vs SMT: Performance Comparison Neural MT vs SMT Handling complex (Chinese) or morphologically rich (Russian) languages NMT better Word reordering NMT better Fluency NMT better Adequacy NMT may give problems (more deviations that make sense, rare words, whole information bits missing) Volume of training data needed Generally, NMT needs more data, but this depends on processing capacity Unpredictable errors More likely (specially if insufficient training data)