SlideShare a Scribd company logo
1 of 24
Natural language processing
Parsing and understanding language
Full Day of Applied AI
Morning
Session 1 Intro to Artificial Intelligence
09:00-09:45 Introduction to Applied AI
09:45-10:00 Coffee and break
Session 2 Live Coding a machine learning app
10:00-10:10 Getting your machine ready for machine learning
10:10-10.20 Training and evaluating the model
10.20-10.50 Improving the model
10.50-11.00 Coffee and break
Session 3 Machine learning in the wild - deployment
11:00-11.15 Coding exercise continued
11:15-11:45 Serving your own machine learning model | Code
11:45-11:55 How to solve problems | interactive exercise
11:55-12:00 Q and A
Lunch
12:00-13:00 Lunch
Afternoon
Session 4 Hello World Deep Learning (MNIST)
13:00-13:15 Deep Learning intro
13:00-13.15 Image recognition and CNNs | Talk |
13:15-13:45 Building your own convolutional neural network | Code |
13:45-14:00 Coffee and break
Session 5 Natural Language Processing
14:00-14.30 Natural language processing | Talk |
14:30-14:45 Working with language | Code |
14:45-15:00 Coffee and break
Session 6 Conversational interfaces and Time Series
14:00-14.20 Conversational interfaces
14:20-14:45 Time Series prediction
14:45-15:00 Coffee and break
Session 7 Generative models and style transfer
16:00-16.30 Generative models | Talk |
16:30-16:45 Trying out GANS and style transfer | Code |
16:45-17:00 Coffee and break
Anton Osika AI Research Engineer Sana Labs AB
anton.osika@gmail.com
Birger Moëll Machine Learning Engineer
birger.moell@gmail.com
ECG
Deep learning for speech
State of the art in machine
learning can understand human
speech well enough to perform
fairly complicated actions based
on speech commands.
Natural Language Processing
Text to speech (Wavenet State of the Art, https://deepmind.com/blog/wavenet-generative-
model-raw-audio)
Speech to text (Alexa, Google Home, Google https://cloud.google.com/speech-to-text/)
Text to vector (Glove, Word2Vec, Bert)
Natural language creation (LSTMs, Generative models, GPT2)
Word vectors
Word vectors are high dimensional representations of language where each word
is assigned a vector based on its closeness to other words. This gives the model a
representation of language that includes bias and changes over time.
Word vector algebra
We can now compare how similar words are
How are word vectors used in ML?
Answer: Transfer learning
Using a model pre-trained on large text databases and then fine-tuning it on the desired task
has revolutionized NLP
Attention is all you need
The progress in NLP has been largely
based on the Attention Mechanism from
https://arxiv.org/abs/1706.03762.
Attention is all you need.
As opposed to directional models the
Attention model reads the entire
sequence of words at once instead of
sequentially.
It is therefore considered “bidirectional”,
though it would be more accurate to say
that it is “non-directional”.
The imagenet moment for NLP
October 2018, BERT Arrives
BERT is hailed as an imagenet moment for
natural language processing
https://thegradient.pub/nlp-imagenet/
Bert Paper
https://arxiv.org/abs/1810.04805
New state of the art on most NLP tasks
https://rajpurkar.github.io/SQuAD-
explorer/explore/1.1/dev/Harvard_Un
iversity.html?model=BERT%20(ense
mble)%20(Google%20AI%20Langua
ge)&version=1.1
Training BERT
Training BERT
How BERT works
BERT works using attention for
computing how much each word should
be combined with each other word to
compute their collective meaning.
http://jalammar.github.io/illustrated-bert/
Query and Key vectors “attend” Value vectors
Query, Key and Value
vectors gives each
word knowledge
about how much it
should be combined
with other words.
Attention visualized
The trainable Query, Key and
Value vectors result in what we
call “attention”.
The BERT encoder uses stacked attention
layers that does the attention computation
many times in parallel.
Output from the encoder is directly
mapped to the predicted output sequence.
Stacked attention heads
Fine tuning on the desired task
Fine tuning on the desired task
There exists several implementations of BERT
that gives us access to BERT-tensors to work
with.
However, in order to use BERT for language
tasks we need to train a classifier for our specific
problem.
This can be done with a neural network that uses
BERT-encoded word-vectors with labels as their
input (for classification).
Tensorflow Model
https://github.com/google-
research/bert
Pytorch Model
https://github.com/huggingfa
ce/pytorch-pretrained-BERT
Bert as Service
https://github.com/hanxiao/b
ert-as-service
GPT-2
GPT-2 is a model
created by Open AI
that improves state of
the art in language
creation.
Because of fears of
malicious use the full
model was never
released.
https://talktotransformer.com/
Lets get started coding
Open up the notebooks inside Natural
Language Processing to train your own
deep neural network for natural language
processing.
Almost human level...
Almost human level...

More Related Content

What's hot

MT and Translator's Tools
MT and Translator's ToolsMT and Translator's Tools
MT and Translator's ToolsJim O'Regan
 
Neural machine translation by jointly learning to align and translate
Neural machine translation by jointly learning to align and translateNeural machine translation by jointly learning to align and translate
Neural machine translation by jointly learning to align and translatesotanemoto
 
Moving to neural machine translation at google - gopro-meetup
Moving to neural machine translation at google  - gopro-meetupMoving to neural machine translation at google  - gopro-meetup
Moving to neural machine translation at google - gopro-meetupChester Chen
 
Python an-intro youtube-livestream-day1
Python an-intro youtube-livestream-day1Python an-intro youtube-livestream-day1
Python an-intro youtube-livestream-day1MAHALAKSHMI P
 
Cs8392 u1-1-oop intro
Cs8392 u1-1-oop introCs8392 u1-1-oop intro
Cs8392 u1-1-oop introRajasekaran S
 

What's hot (6)

MT and Translator's Tools
MT and Translator's ToolsMT and Translator's Tools
MT and Translator's Tools
 
Neural machine translation by jointly learning to align and translate
Neural machine translation by jointly learning to align and translateNeural machine translation by jointly learning to align and translate
Neural machine translation by jointly learning to align and translate
 
Moving to neural machine translation at google - gopro-meetup
Moving to neural machine translation at google  - gopro-meetupMoving to neural machine translation at google  - gopro-meetup
Moving to neural machine translation at google - gopro-meetup
 
1-oop java-object
1-oop java-object1-oop java-object
1-oop java-object
 
Python an-intro youtube-livestream-day1
Python an-intro youtube-livestream-day1Python an-intro youtube-livestream-day1
Python an-intro youtube-livestream-day1
 
Cs8392 u1-1-oop intro
Cs8392 u1-1-oop introCs8392 u1-1-oop intro
Cs8392 u1-1-oop intro
 

Similar to Natural language processing

Conversational interfaces and time series prediction
Conversational interfaces and time series predictionConversational interfaces and time series prediction
Conversational interfaces and time series predictionBirger Moell
 
Natural Language Processing - Research and Application Trends
Natural Language Processing - Research and Application TrendsNatural Language Processing - Research and Application Trends
Natural Language Processing - Research and Application TrendsShreyas Suresh Rao
 
Envisioning the Future of Language Workbenches
Envisioning the Future of Language WorkbenchesEnvisioning the Future of Language Workbenches
Envisioning the Future of Language WorkbenchesMarkus Voelter
 
Modelling and Programming: Isn’t it all the same?
Modelling and Programming: Isn’t it all the same?Modelling and Programming: Isn’t it all the same?
Modelling and Programming: Isn’t it all the same?CHOOSE
 
IRJET - Storytelling App for Children with Hearing Impairment using Natur...
IRJET -  	  Storytelling App for Children with Hearing Impairment using Natur...IRJET -  	  Storytelling App for Children with Hearing Impairment using Natur...
IRJET - Storytelling App for Children with Hearing Impairment using Natur...IRJET Journal
 
Stream SQL eventflow visual programming for real programmers presentation
Stream SQL eventflow visual programming for real programmers presentationStream SQL eventflow visual programming for real programmers presentation
Stream SQL eventflow visual programming for real programmers presentationstreambase
 
BERT - Part 1 Learning Notes of Senthil Kumar
BERT - Part 1 Learning Notes of Senthil KumarBERT - Part 1 Learning Notes of Senthil Kumar
BERT - Part 1 Learning Notes of Senthil KumarSenthil Kumar M
 
Deep Learning for NLP Applications
Deep Learning for NLP ApplicationsDeep Learning for NLP Applications
Deep Learning for NLP ApplicationsSamiur Rahman
 
Build your own Language - Why and How?
Build your own Language - Why and How?Build your own Language - Why and How?
Build your own Language - Why and How?Markus Voelter
 
Tomáš Mikolov - Distributed Representations for NLP
Tomáš Mikolov - Distributed Representations for NLPTomáš Mikolov - Distributed Representations for NLP
Tomáš Mikolov - Distributed Representations for NLPMachine Learning Prague
 
Machine learning in the wild deployment
Machine learning in the wild deploymentMachine learning in the wild deployment
Machine learning in the wild deploymentBirger Moell
 
Smart modeling of smart software
Smart modeling of smart softwareSmart modeling of smart software
Smart modeling of smart softwareJordi Cabot
 
Importance Of Being Driven
Importance Of Being DrivenImportance Of Being Driven
Importance Of Being DrivenAntonio Terreno
 
Pharo: A Reflective System
Pharo: A Reflective SystemPharo: A Reflective System
Pharo: A Reflective SystemMarcus Denker
 
ورشة تضمين الكلمات في التعلم العميق Word embeddings workshop
ورشة تضمين الكلمات في التعلم العميق Word embeddings workshopورشة تضمين الكلمات في التعلم العميق Word embeddings workshop
ورشة تضمين الكلمات في التعلم العميق Word embeddings workshopiwan_rg
 

Similar to Natural language processing (20)

Conversational interfaces and time series prediction
Conversational interfaces and time series predictionConversational interfaces and time series prediction
Conversational interfaces and time series prediction
 
Natural Language Processing - Research and Application Trends
Natural Language Processing - Research and Application TrendsNatural Language Processing - Research and Application Trends
Natural Language Processing - Research and Application Trends
 
Envisioning the Future of Language Workbenches
Envisioning the Future of Language WorkbenchesEnvisioning the Future of Language Workbenches
Envisioning the Future of Language Workbenches
 
Modelling and Programming: Isn’t it all the same?
Modelling and Programming: Isn’t it all the same?Modelling and Programming: Isn’t it all the same?
Modelling and Programming: Isn’t it all the same?
 
D1803041822
D1803041822D1803041822
D1803041822
 
IRJET - Storytelling App for Children with Hearing Impairment using Natur...
IRJET -  	  Storytelling App for Children with Hearing Impairment using Natur...IRJET -  	  Storytelling App for Children with Hearing Impairment using Natur...
IRJET - Storytelling App for Children with Hearing Impairment using Natur...
 
Stream SQL eventflow visual programming for real programmers presentation
Stream SQL eventflow visual programming for real programmers presentationStream SQL eventflow visual programming for real programmers presentation
Stream SQL eventflow visual programming for real programmers presentation
 
OOP Java
OOP JavaOOP Java
OOP Java
 
BERT - Part 1 Learning Notes of Senthil Kumar
BERT - Part 1 Learning Notes of Senthil KumarBERT - Part 1 Learning Notes of Senthil Kumar
BERT - Part 1 Learning Notes of Senthil Kumar
 
Chatbot_Presentation
Chatbot_PresentationChatbot_Presentation
Chatbot_Presentation
 
Deep Learning for NLP Applications
Deep Learning for NLP ApplicationsDeep Learning for NLP Applications
Deep Learning for NLP Applications
 
Build your own Language - Why and How?
Build your own Language - Why and How?Build your own Language - Why and How?
Build your own Language - Why and How?
 
Unit 1
Unit 1Unit 1
Unit 1
 
Tomáš Mikolov - Distributed Representations for NLP
Tomáš Mikolov - Distributed Representations for NLPTomáš Mikolov - Distributed Representations for NLP
Tomáš Mikolov - Distributed Representations for NLP
 
Intro1
Intro1Intro1
Intro1
 
Machine learning in the wild deployment
Machine learning in the wild deploymentMachine learning in the wild deployment
Machine learning in the wild deployment
 
Smart modeling of smart software
Smart modeling of smart softwareSmart modeling of smart software
Smart modeling of smart software
 
Importance Of Being Driven
Importance Of Being DrivenImportance Of Being Driven
Importance Of Being Driven
 
Pharo: A Reflective System
Pharo: A Reflective SystemPharo: A Reflective System
Pharo: A Reflective System
 
ورشة تضمين الكلمات في التعلم العميق Word embeddings workshop
ورشة تضمين الكلمات في التعلم العميق Word embeddings workshopورشة تضمين الكلمات في التعلم العميق Word embeddings workshop
ورشة تضمين الكلمات في التعلم العميق Word embeddings workshop
 

Recently uploaded

Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 

Recently uploaded (20)

Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 

Natural language processing

  • 1. Natural language processing Parsing and understanding language
  • 2. Full Day of Applied AI Morning Session 1 Intro to Artificial Intelligence 09:00-09:45 Introduction to Applied AI 09:45-10:00 Coffee and break Session 2 Live Coding a machine learning app 10:00-10:10 Getting your machine ready for machine learning 10:10-10.20 Training and evaluating the model 10.20-10.50 Improving the model 10.50-11.00 Coffee and break Session 3 Machine learning in the wild - deployment 11:00-11.15 Coding exercise continued 11:15-11:45 Serving your own machine learning model | Code 11:45-11:55 How to solve problems | interactive exercise 11:55-12:00 Q and A Lunch 12:00-13:00 Lunch Afternoon Session 4 Hello World Deep Learning (MNIST) 13:00-13:15 Deep Learning intro 13:00-13.15 Image recognition and CNNs | Talk | 13:15-13:45 Building your own convolutional neural network | Code | 13:45-14:00 Coffee and break Session 5 Natural Language Processing 14:00-14.30 Natural language processing | Talk | 14:30-14:45 Working with language | Code | 14:45-15:00 Coffee and break Session 6 Conversational interfaces and Time Series 14:00-14.20 Conversational interfaces 14:20-14:45 Time Series prediction 14:45-15:00 Coffee and break Session 7 Generative models and style transfer 16:00-16.30 Generative models | Talk | 16:30-16:45 Trying out GANS and style transfer | Code | 16:45-17:00 Coffee and break Anton Osika AI Research Engineer Sana Labs AB anton.osika@gmail.com Birger Moëll Machine Learning Engineer birger.moell@gmail.com
  • 3. ECG
  • 4. Deep learning for speech State of the art in machine learning can understand human speech well enough to perform fairly complicated actions based on speech commands.
  • 5. Natural Language Processing Text to speech (Wavenet State of the Art, https://deepmind.com/blog/wavenet-generative- model-raw-audio) Speech to text (Alexa, Google Home, Google https://cloud.google.com/speech-to-text/) Text to vector (Glove, Word2Vec, Bert) Natural language creation (LSTMs, Generative models, GPT2)
  • 6. Word vectors Word vectors are high dimensional representations of language where each word is assigned a vector based on its closeness to other words. This gives the model a representation of language that includes bias and changes over time.
  • 8. We can now compare how similar words are
  • 9. How are word vectors used in ML? Answer: Transfer learning Using a model pre-trained on large text databases and then fine-tuning it on the desired task has revolutionized NLP
  • 10. Attention is all you need The progress in NLP has been largely based on the Attention Mechanism from https://arxiv.org/abs/1706.03762. Attention is all you need. As opposed to directional models the Attention model reads the entire sequence of words at once instead of sequentially. It is therefore considered “bidirectional”, though it would be more accurate to say that it is “non-directional”.
  • 11. The imagenet moment for NLP October 2018, BERT Arrives BERT is hailed as an imagenet moment for natural language processing https://thegradient.pub/nlp-imagenet/ Bert Paper https://arxiv.org/abs/1810.04805
  • 12. New state of the art on most NLP tasks https://rajpurkar.github.io/SQuAD- explorer/explore/1.1/dev/Harvard_Un iversity.html?model=BERT%20(ense mble)%20(Google%20AI%20Langua ge)&version=1.1
  • 15. How BERT works BERT works using attention for computing how much each word should be combined with each other word to compute their collective meaning. http://jalammar.github.io/illustrated-bert/
  • 16. Query and Key vectors “attend” Value vectors Query, Key and Value vectors gives each word knowledge about how much it should be combined with other words.
  • 17. Attention visualized The trainable Query, Key and Value vectors result in what we call “attention”.
  • 18. The BERT encoder uses stacked attention layers that does the attention computation many times in parallel. Output from the encoder is directly mapped to the predicted output sequence. Stacked attention heads
  • 19. Fine tuning on the desired task
  • 20. Fine tuning on the desired task There exists several implementations of BERT that gives us access to BERT-tensors to work with. However, in order to use BERT for language tasks we need to train a classifier for our specific problem. This can be done with a neural network that uses BERT-encoded word-vectors with labels as their input (for classification). Tensorflow Model https://github.com/google- research/bert Pytorch Model https://github.com/huggingfa ce/pytorch-pretrained-BERT Bert as Service https://github.com/hanxiao/b ert-as-service
  • 21. GPT-2 GPT-2 is a model created by Open AI that improves state of the art in language creation. Because of fears of malicious use the full model was never released. https://talktotransformer.com/
  • 22. Lets get started coding Open up the notebooks inside Natural Language Processing to train your own deep neural network for natural language processing.

Editor's Notes

  1. Birger
  2. Add comment about how good it is
  3. Stanford Squah