SlideShare a Scribd company logo
Deep Learning and Modern Natural
Language Processing
Zachary Brown, Lead Data Scientist, S&P Global
Outline
• Neural Methods for Natural Language Processing
• Shapes of Natural Language Processing Tasks
• Perceptron Text Classification
• Local vs. Global Text Representations
• Contextual Representations and Sequence Modeling
2
Neural Methods for Natural Language
Processing
Neural Methods for Natural Language
Processing
• Natural Language Processing (NLP) has moved largely to neural
methods in recent years
4
Neural Methods for Natural Language
Processing
• Natural Language Processing (NLP) has moved largely to neural
methods in recent years
5
• Traditional NLP builds on years of research into
language representation
• Theoretical foundations can lead to model rigidity
• Tasks often rely on manually generated and
curated dictionaries and thesauruses
• Built upon local word representations
Neural Methods for Natural Language
Processing
• Natural Language Processing (NLP) has moved largely to neural
methods in recent years
6
• Few to no assumptions need to be made
• Active area of research; most open-source
• Ability to learn global and contextualized
word representations
• Purpose-built model architectures
Neural Methods for Natural Language
Processing
• Natural Language Processing (NLP) has moved largely to neural
methods in recent years
7
• Few to no assumptions need to be made
• Active area of research; most open-source
• Ability to learn global and contextualized
word representations
• Purpose-built model architectures
Shapes of Natural Language
Processing Tasks
Shapes of Natural Language Processing
Tasks
• A general task in natural language processing often takes the form:
9
Shapes of Natural Language Processing
Tasks
• For binary classification processes (relevance), our target is a single
number, often interpreted as a probability
10
Shapes of Natural Language Processing
Tasks
• For multi-class classification processes (type of text), our target is a
set of probabilities, one for each of the output classes
11
Shapes of Natural Language Processing
Tasks
• For sequential classification (e.g. LM, NER, POS) the target is a
probability of each class for each element in the input
12
Shapes of Natural Language Processing
Tasks
• In a traditional machine learning pipeline, vectorization (feature
engineering) process is often a (very) time consuming process
13
80-90%
Shapes of Natural Language Processing
Tasks
• A relatively small proportion of time is spent on the actual modeling
14
10-20%
Shapes of Natural Language Processing
Tasks
• Neural networks allow us to develop purpose-built architectures to
solve tasks, that learn the appropriate vectorization for a task
15
100%
Perceptron Text Classification
Perceptron Text Classification
• To introduce the shape of information as it flows through a neural
network, we'll first look at a network that only handles classification
17
Perceptron Text Classification
• For the vectorization, we'll assume that we've converted our text
into a vector using a count-based method like tf-idf
18
tf-idf
Perceptron Text Classification
• A perceptron is one of the simplest neural network architectures,
and is a good fit for this task
19
Perceptron Text Classification
• A perceptron is one of the simplest neural network architectures,
and is a good fit for this task
20
input
hidden
(linear)
activation
output
Perceptron Text Classification
• The hidden layer represents the weights that will be optimized by
the deep learning framework.
21
input
hidden
(linear)
activation
output
weights
Perceptron Text Classification
• If we want to change our task to multiclass classification, we can
simply change the size of our hidden layer (+ minor mods)
22
Perceptron Text Classification
• The result of this is that we now have a matrix of weights to optimize
23
weights
Local vs. Global Text Representations
Local vs. Global Text Representations
• Let's look back to the problem of creating a vector representation for
our text
25
tf-idf
Local vs. Global Text Representations
• Further, let's only consider the task of how we'd represent single
words or tokens as vectors
26
dog
Local vs. Global Text Representations
• Traditional approaches to word representations treat each word as
a unique entity
27
Local vs. Global Text Representations
• Traditional approaches to word representations treat each word as
a unique entity
28
Local vs. Global Text Representations
• Traditional approaches to word representations treat each word as
a unique entity
29
Local vs. Global Text Representations
• Traditional approaches to word representations treat each word as
a unique entity
30
Local vs. Global Text Representations
• Modern approaches move to a fixed dimensional vector size, with
dense vectors
31
Local vs. Global Text Representations
• Modern approaches move to a fixed dimensional vector size, with
dense vectors
32
Local vs. Global Text Representations
• Modern approaches move to a fixed dimensional vector size, with
dense vectors
33
Local vs. Global Text Representations
• There are a variety of frameworks available that allow for computing
these vectors in an unsupervised way
34
Contextual Representations and
Sequence Modeling
Contextual Representations and Sequence
Modeling
• Global word representations are a fantastic starting point for many
problems in NLP, but consider the following sentence
36
I'm going to book our vacation then relax and read a good book
Contextual Representations and Sequence
Modeling
• Global word representations are a fantastic starting point for many
problems in NLP, but consider the following sentence
37
I'm going to book our vacation then relax and read a good book
I don't really hate horror movies, but I hate comedies
Contextual Representations and Sequence
Modeling
• Global word representations are a fantastic starting point for many
problems in NLP, but consider the following sentence
38
I don't really hate horror movies, but I hate comedies
Contextual Representations and Sequence
Modeling
• Global word representations are a fantastic starting point for many
problems in NLP, but consider the following sentence
39
Context
Matters
Contextual Representations and Sequence
Modeling
• For modeling tasks where word ordering and context matter,
sequential models are often used. These tasks often take the
following shape:
40
Contextual Representations and Sequence
Modeling
• Recurrent neural networks are a type of neural network architecture
that naturally handles modeling sequential data
41
Contextual Representations and Sequence
Modeling
• This type of network generates a new output vector for each input in
a sequence, and also feeds that same information forward
42
Contextual Representations and Sequence
Modeling
• By feeding the information forward, each subsequent output vector
has contextual information encoded from the preceding words
43
Contextual Representations and Sequence
Modeling
• This type of architecture can be used to build language models,
where the task is to predict the next word in the sequence
44
Contextual Representations and Sequence
Modeling
• It can also be used for problems like named entity recognition
45
animalo o o o animal
Contextual Representations and Sequence
Modeling
• By taking the final vector in the sequence, you can perform tasks
like sentiment classification
46
positive
Contextual Representations and Sequence
Modeling
• For all of these different types of tasks, a network similar to the
perceptron can be placed at the end to carry out the final
classification of each word
47
Contextual Representations and Sequence
Modeling
• For all of these different types of tasks, a network similar to the
perceptron can be placed at the end to carry out the final
classification of each word, or the classification of the whole
sequence
48
Contextual Representations and Sequence
Modeling
• In a similar manner, these individual elements can be combined in a
variety of ways to tackle very complex tasks
49
Contextual Representations and Sequence
Modeling
• In a similar manner, these individual elements can be combined in a
variety of ways to tackle very complex tasks
50
Contextual Representations and Sequence
Modeling
• In a similar manner, these individual elements can be combined in a
variety of ways to tackle very complex tasks
51
Contextual Representations and Sequence
Modeling
• In a similar manner, these individual elements can be combined in a
variety of ways to tackle very complex tasks
52
Thank you.

More Related Content

What's hot

Frontiers of Natural Language Processing
Frontiers of Natural Language ProcessingFrontiers of Natural Language Processing
Frontiers of Natural Language Processing
Sebastian Ruder
 
Deep Learning for Information Retrieval
Deep Learning for Information RetrievalDeep Learning for Information Retrieval
Deep Learning for Information Retrieval
Roelof Pieters
 
Deep learning for nlp
Deep learning for nlpDeep learning for nlp
Deep learning for nlp
Viet-Trung TRAN
 
Word2vec slide(lab seminar)
Word2vec slide(lab seminar)Word2vec slide(lab seminar)
Word2vec slide(lab seminar)
Jinpyo Lee
 
NLP Bootcamp
NLP BootcampNLP Bootcamp
NLP Bootcamp
Anuj Gupta
 
Representation Learning of Vectors of Words and Phrases
Representation Learning of Vectors of Words and PhrasesRepresentation Learning of Vectors of Words and Phrases
Representation Learning of Vectors of Words and Phrases
Felipe Moraes
 
NLP Bootcamp 2018 : Representation Learning of text for NLP
NLP Bootcamp 2018 : Representation Learning of text for NLPNLP Bootcamp 2018 : Representation Learning of text for NLP
NLP Bootcamp 2018 : Representation Learning of text for NLP
Anuj Gupta
 
Anthiil Inside workshop on NLP
Anthiil Inside workshop on NLPAnthiil Inside workshop on NLP
Anthiil Inside workshop on NLP
Satyam Saxena
 
1910 HCLT
1910 HCLT1910 HCLT
1910 HCLT
WarNik Chow
 
Networks and Natural Language Processing
Networks and Natural Language ProcessingNetworks and Natural Language Processing
Networks and Natural Language Processing
Ahmed Magdy Ezzeldin, MSc.
 
Lecture 1: Semantic Analysis in Language Technology
Lecture 1: Semantic Analysis in Language TechnologyLecture 1: Semantic Analysis in Language Technology
Lecture 1: Semantic Analysis in Language Technology
Marina Santini
 
What is word2vec?
What is word2vec?What is word2vec?
What is word2vec?
Traian Rebedea
 
Learning to understand phrases by embedding the dictionary
Learning to understand phrases by embedding the dictionaryLearning to understand phrases by embedding the dictionary
Learning to understand phrases by embedding the dictionary
Roelof Pieters
 
Is acquiring knowledge of verb subcategorization in English easier? A partial...
Is acquiring knowledge of verb subcategorization in English easier? A partial...Is acquiring knowledge of verb subcategorization in English easier? A partial...
Is acquiring knowledge of verb subcategorization in English easier? A partial...
Yu Tamura
 
Word Embeddings, why the hype ?
Word Embeddings, why the hype ? Word Embeddings, why the hype ?
Word Embeddings, why the hype ?
Hady Elsahar
 
Thai Word Embedding with Tensorflow
Thai Word Embedding with Tensorflow Thai Word Embedding with Tensorflow
Thai Word Embedding with Tensorflow
Kobkrit Viriyayudhakorn
 
Intent Classifier with Facebook fastText
Intent Classifier with Facebook fastTextIntent Classifier with Facebook fastText
Intent Classifier with Facebook fastText
Bayu Aldi Yansyah
 
(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结
君 廖
 

What's hot (20)

Frontiers of Natural Language Processing
Frontiers of Natural Language ProcessingFrontiers of Natural Language Processing
Frontiers of Natural Language Processing
 
Deep Learning for Information Retrieval
Deep Learning for Information RetrievalDeep Learning for Information Retrieval
Deep Learning for Information Retrieval
 
Deep learning for nlp
Deep learning for nlpDeep learning for nlp
Deep learning for nlp
 
Word2vec slide(lab seminar)
Word2vec slide(lab seminar)Word2vec slide(lab seminar)
Word2vec slide(lab seminar)
 
NLP Bootcamp
NLP BootcampNLP Bootcamp
NLP Bootcamp
 
Representation Learning of Vectors of Words and Phrases
Representation Learning of Vectors of Words and PhrasesRepresentation Learning of Vectors of Words and Phrases
Representation Learning of Vectors of Words and Phrases
 
NLP Bootcamp 2018 : Representation Learning of text for NLP
NLP Bootcamp 2018 : Representation Learning of text for NLPNLP Bootcamp 2018 : Representation Learning of text for NLP
NLP Bootcamp 2018 : Representation Learning of text for NLP
 
Anthiil Inside workshop on NLP
Anthiil Inside workshop on NLPAnthiil Inside workshop on NLP
Anthiil Inside workshop on NLP
 
Arabic question answering ‫‬
Arabic question answering ‫‬Arabic question answering ‫‬
Arabic question answering ‫‬
 
1910 HCLT
1910 HCLT1910 HCLT
1910 HCLT
 
Networks and Natural Language Processing
Networks and Natural Language ProcessingNetworks and Natural Language Processing
Networks and Natural Language Processing
 
Lecture 1: Semantic Analysis in Language Technology
Lecture 1: Semantic Analysis in Language TechnologyLecture 1: Semantic Analysis in Language Technology
Lecture 1: Semantic Analysis in Language Technology
 
What is word2vec?
What is word2vec?What is word2vec?
What is word2vec?
 
Learning to understand phrases by embedding the dictionary
Learning to understand phrases by embedding the dictionaryLearning to understand phrases by embedding the dictionary
Learning to understand phrases by embedding the dictionary
 
Is acquiring knowledge of verb subcategorization in English easier? A partial...
Is acquiring knowledge of verb subcategorization in English easier? A partial...Is acquiring knowledge of verb subcategorization in English easier? A partial...
Is acquiring knowledge of verb subcategorization in English easier? A partial...
 
Language models
Language modelsLanguage models
Language models
 
Word Embeddings, why the hype ?
Word Embeddings, why the hype ? Word Embeddings, why the hype ?
Word Embeddings, why the hype ?
 
Thai Word Embedding with Tensorflow
Thai Word Embedding with Tensorflow Thai Word Embedding with Tensorflow
Thai Word Embedding with Tensorflow
 
Intent Classifier with Facebook fastText
Intent Classifier with Facebook fastTextIntent Classifier with Facebook fastText
Intent Classifier with Facebook fastText
 
(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结(Deep) Neural Networks在 NLP 和 Text Mining 总结
(Deep) Neural Networks在 NLP 和 Text Mining 总结
 

Similar to Deep Learning and Modern Natural Language Processing (AnacondaCon2019)

A Panorama of Natural Language Processing
A Panorama of Natural Language ProcessingA Panorama of Natural Language Processing
A Panorama of Natural Language Processing
Ted Xiao
 
Natural Language Processing (NLP)
Natural Language Processing (NLP)Natural Language Processing (NLP)
Natural Language Processing (NLP)
Abdullah al Mamun
 
https://www.slideshare.net/amaresimachew/hot-topics-132093738
https://www.slideshare.net/amaresimachew/hot-topics-132093738https://www.slideshare.net/amaresimachew/hot-topics-132093738
https://www.slideshare.net/amaresimachew/hot-topics-132093738
Assosa University
 
AINL 2016: Nikolenko
AINL 2016: NikolenkoAINL 2016: Nikolenko
AINL 2016: Nikolenko
Lidia Pivovarova
 
Natural Language Processing Advancements By Deep Learning - A Survey
Natural Language Processing Advancements By Deep Learning - A SurveyNatural Language Processing Advancements By Deep Learning - A Survey
Natural Language Processing Advancements By Deep Learning - A Survey
AkshayaNagarajan10
 
Beyond the Symbols: A 30-minute Overview of NLP
Beyond the Symbols: A 30-minute Overview of NLPBeyond the Symbols: A 30-minute Overview of NLP
Beyond the Symbols: A 30-minute Overview of NLP
MENGSAYLOEM1
 
Building a Neural Machine Translation System From Scratch
Building a Neural Machine Translation System From ScratchBuilding a Neural Machine Translation System From Scratch
Building a Neural Machine Translation System From Scratch
Natasha Latysheva
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word Embeddings
Roelof Pieters
 
Intro to nlp
Intro to nlpIntro to nlp
Intro to nlp
ankit_ppt
 
introtonlp-190218095523 (1).pdf
introtonlp-190218095523 (1).pdfintrotonlp-190218095523 (1).pdf
introtonlp-190218095523 (1).pdf
AdityaMishra178868
 
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty DialogueTransformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
Jinho Choi
 
Word embedding
Word embedding Word embedding
Word embedding
ShivaniChoudhary74
 
wordembedding.pptx
wordembedding.pptxwordembedding.pptx
wordembedding.pptx
JOBANPREETSINGH62
 
Artificial Intelligence Notes Unit 4
Artificial Intelligence Notes Unit 4Artificial Intelligence Notes Unit 4
Artificial Intelligence Notes Unit 4
DigiGurukul
 
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Young Seok Kim
 
Word embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTMWord embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTM
Divya Gera
 
Deep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word EmbeddingsDeep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word Embeddings
Roelof Pieters
 
Introduction to natural language processing (NLP)
Introduction to natural language processing (NLP)Introduction to natural language processing (NLP)
Introduction to natural language processing (NLP)
Alia Hamwi
 
Natural Language Processing Course in AI
Natural Language Processing Course in AINatural Language Processing Course in AI
Natural Language Processing Course in AI
SATHYANARAYANAKB
 
Machine Translation Introduction
Machine Translation IntroductionMachine Translation Introduction
Machine Translation Introduction
nlab_utokyo
 

Similar to Deep Learning and Modern Natural Language Processing (AnacondaCon2019) (20)

A Panorama of Natural Language Processing
A Panorama of Natural Language ProcessingA Panorama of Natural Language Processing
A Panorama of Natural Language Processing
 
Natural Language Processing (NLP)
Natural Language Processing (NLP)Natural Language Processing (NLP)
Natural Language Processing (NLP)
 
https://www.slideshare.net/amaresimachew/hot-topics-132093738
https://www.slideshare.net/amaresimachew/hot-topics-132093738https://www.slideshare.net/amaresimachew/hot-topics-132093738
https://www.slideshare.net/amaresimachew/hot-topics-132093738
 
AINL 2016: Nikolenko
AINL 2016: NikolenkoAINL 2016: Nikolenko
AINL 2016: Nikolenko
 
Natural Language Processing Advancements By Deep Learning - A Survey
Natural Language Processing Advancements By Deep Learning - A SurveyNatural Language Processing Advancements By Deep Learning - A Survey
Natural Language Processing Advancements By Deep Learning - A Survey
 
Beyond the Symbols: A 30-minute Overview of NLP
Beyond the Symbols: A 30-minute Overview of NLPBeyond the Symbols: A 30-minute Overview of NLP
Beyond the Symbols: A 30-minute Overview of NLP
 
Building a Neural Machine Translation System From Scratch
Building a Neural Machine Translation System From ScratchBuilding a Neural Machine Translation System From Scratch
Building a Neural Machine Translation System From Scratch
 
Deep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word EmbeddingsDeep Learning for Natural Language Processing: Word Embeddings
Deep Learning for Natural Language Processing: Word Embeddings
 
Intro to nlp
Intro to nlpIntro to nlp
Intro to nlp
 
introtonlp-190218095523 (1).pdf
introtonlp-190218095523 (1).pdfintrotonlp-190218095523 (1).pdf
introtonlp-190218095523 (1).pdf
 
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty DialogueTransformers to Learn Hierarchical Contexts in Multiparty Dialogue
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue
 
Word embedding
Word embedding Word embedding
Word embedding
 
wordembedding.pptx
wordembedding.pptxwordembedding.pptx
wordembedding.pptx
 
Artificial Intelligence Notes Unit 4
Artificial Intelligence Notes Unit 4Artificial Intelligence Notes Unit 4
Artificial Intelligence Notes Unit 4
 
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
 
Word embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTMWord embeddings, RNN, GRU and LSTM
Word embeddings, RNN, GRU and LSTM
 
Deep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word EmbeddingsDeep Learning for NLP: An Introduction to Neural Word Embeddings
Deep Learning for NLP: An Introduction to Neural Word Embeddings
 
Introduction to natural language processing (NLP)
Introduction to natural language processing (NLP)Introduction to natural language processing (NLP)
Introduction to natural language processing (NLP)
 
Natural Language Processing Course in AI
Natural Language Processing Course in AINatural Language Processing Course in AI
Natural Language Processing Course in AI
 
Machine Translation Introduction
Machine Translation IntroductionMachine Translation Introduction
Machine Translation Introduction
 

More from Zachary S. Brown

Working in NLP in the Age of Large Language Models
Working in NLP in the Age of Large Language ModelsWorking in NLP in the Age of Large Language Models
Working in NLP in the Age of Large Language Models
Zachary S. Brown
 
Teaching Machines to Listen: An Introduction to Automatic Speech Recognition
Teaching Machines to Listen: An Introduction to Automatic Speech RecognitionTeaching Machines to Listen: An Introduction to Automatic Speech Recognition
Teaching Machines to Listen: An Introduction to Automatic Speech Recognition
Zachary S. Brown
 
Building and Deploying Scalable NLP Model Services
Building and Deploying Scalable NLP Model ServicesBuilding and Deploying Scalable NLP Model Services
Building and Deploying Scalable NLP Model Services
Zachary S. Brown
 
Deep Learning and Modern NLP
Deep Learning and Modern NLPDeep Learning and Modern NLP
Deep Learning and Modern NLP
Zachary S. Brown
 
Cyber Threat Ranking using READ
Cyber Threat Ranking using READCyber Threat Ranking using READ
Cyber Threat Ranking using READ
Zachary S. Brown
 
Deep Domain
Deep DomainDeep Domain
Deep Domain
Zachary S. Brown
 

More from Zachary S. Brown (6)

Working in NLP in the Age of Large Language Models
Working in NLP in the Age of Large Language ModelsWorking in NLP in the Age of Large Language Models
Working in NLP in the Age of Large Language Models
 
Teaching Machines to Listen: An Introduction to Automatic Speech Recognition
Teaching Machines to Listen: An Introduction to Automatic Speech RecognitionTeaching Machines to Listen: An Introduction to Automatic Speech Recognition
Teaching Machines to Listen: An Introduction to Automatic Speech Recognition
 
Building and Deploying Scalable NLP Model Services
Building and Deploying Scalable NLP Model ServicesBuilding and Deploying Scalable NLP Model Services
Building and Deploying Scalable NLP Model Services
 
Deep Learning and Modern NLP
Deep Learning and Modern NLPDeep Learning and Modern NLP
Deep Learning and Modern NLP
 
Cyber Threat Ranking using READ
Cyber Threat Ranking using READCyber Threat Ranking using READ
Cyber Threat Ranking using READ
 
Deep Domain
Deep DomainDeep Domain
Deep Domain
 

Recently uploaded

When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
Elena Simperl
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
DianaGray10
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 

Recently uploaded (20)

When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 

Deep Learning and Modern Natural Language Processing (AnacondaCon2019)

  • 1. Deep Learning and Modern Natural Language Processing Zachary Brown, Lead Data Scientist, S&P Global
  • 2. Outline • Neural Methods for Natural Language Processing • Shapes of Natural Language Processing Tasks • Perceptron Text Classification • Local vs. Global Text Representations • Contextual Representations and Sequence Modeling 2
  • 3. Neural Methods for Natural Language Processing
  • 4. Neural Methods for Natural Language Processing • Natural Language Processing (NLP) has moved largely to neural methods in recent years 4
  • 5. Neural Methods for Natural Language Processing • Natural Language Processing (NLP) has moved largely to neural methods in recent years 5 • Traditional NLP builds on years of research into language representation • Theoretical foundations can lead to model rigidity • Tasks often rely on manually generated and curated dictionaries and thesauruses • Built upon local word representations
  • 6. Neural Methods for Natural Language Processing • Natural Language Processing (NLP) has moved largely to neural methods in recent years 6 • Few to no assumptions need to be made • Active area of research; most open-source • Ability to learn global and contextualized word representations • Purpose-built model architectures
  • 7. Neural Methods for Natural Language Processing • Natural Language Processing (NLP) has moved largely to neural methods in recent years 7 • Few to no assumptions need to be made • Active area of research; most open-source • Ability to learn global and contextualized word representations • Purpose-built model architectures
  • 8. Shapes of Natural Language Processing Tasks
  • 9. Shapes of Natural Language Processing Tasks • A general task in natural language processing often takes the form: 9
  • 10. Shapes of Natural Language Processing Tasks • For binary classification processes (relevance), our target is a single number, often interpreted as a probability 10
  • 11. Shapes of Natural Language Processing Tasks • For multi-class classification processes (type of text), our target is a set of probabilities, one for each of the output classes 11
  • 12. Shapes of Natural Language Processing Tasks • For sequential classification (e.g. LM, NER, POS) the target is a probability of each class for each element in the input 12
  • 13. Shapes of Natural Language Processing Tasks • In a traditional machine learning pipeline, vectorization (feature engineering) process is often a (very) time consuming process 13 80-90%
  • 14. Shapes of Natural Language Processing Tasks • A relatively small proportion of time is spent on the actual modeling 14 10-20%
  • 15. Shapes of Natural Language Processing Tasks • Neural networks allow us to develop purpose-built architectures to solve tasks, that learn the appropriate vectorization for a task 15 100%
  • 17. Perceptron Text Classification • To introduce the shape of information as it flows through a neural network, we'll first look at a network that only handles classification 17
  • 18. Perceptron Text Classification • For the vectorization, we'll assume that we've converted our text into a vector using a count-based method like tf-idf 18 tf-idf
  • 19. Perceptron Text Classification • A perceptron is one of the simplest neural network architectures, and is a good fit for this task 19
  • 20. Perceptron Text Classification • A perceptron is one of the simplest neural network architectures, and is a good fit for this task 20 input hidden (linear) activation output
  • 21. Perceptron Text Classification • The hidden layer represents the weights that will be optimized by the deep learning framework. 21 input hidden (linear) activation output weights
  • 22. Perceptron Text Classification • If we want to change our task to multiclass classification, we can simply change the size of our hidden layer (+ minor mods) 22
  • 23. Perceptron Text Classification • The result of this is that we now have a matrix of weights to optimize 23 weights
  • 24. Local vs. Global Text Representations
  • 25. Local vs. Global Text Representations • Let's look back to the problem of creating a vector representation for our text 25 tf-idf
  • 26. Local vs. Global Text Representations • Further, let's only consider the task of how we'd represent single words or tokens as vectors 26 dog
  • 27. Local vs. Global Text Representations • Traditional approaches to word representations treat each word as a unique entity 27
  • 28. Local vs. Global Text Representations • Traditional approaches to word representations treat each word as a unique entity 28
  • 29. Local vs. Global Text Representations • Traditional approaches to word representations treat each word as a unique entity 29
  • 30. Local vs. Global Text Representations • Traditional approaches to word representations treat each word as a unique entity 30
  • 31. Local vs. Global Text Representations • Modern approaches move to a fixed dimensional vector size, with dense vectors 31
  • 32. Local vs. Global Text Representations • Modern approaches move to a fixed dimensional vector size, with dense vectors 32
  • 33. Local vs. Global Text Representations • Modern approaches move to a fixed dimensional vector size, with dense vectors 33
  • 34. Local vs. Global Text Representations • There are a variety of frameworks available that allow for computing these vectors in an unsupervised way 34
  • 36. Contextual Representations and Sequence Modeling • Global word representations are a fantastic starting point for many problems in NLP, but consider the following sentence 36 I'm going to book our vacation then relax and read a good book
  • 37. Contextual Representations and Sequence Modeling • Global word representations are a fantastic starting point for many problems in NLP, but consider the following sentence 37 I'm going to book our vacation then relax and read a good book
  • 38. I don't really hate horror movies, but I hate comedies Contextual Representations and Sequence Modeling • Global word representations are a fantastic starting point for many problems in NLP, but consider the following sentence 38
  • 39. I don't really hate horror movies, but I hate comedies Contextual Representations and Sequence Modeling • Global word representations are a fantastic starting point for many problems in NLP, but consider the following sentence 39 Context Matters
  • 40. Contextual Representations and Sequence Modeling • For modeling tasks where word ordering and context matter, sequential models are often used. These tasks often take the following shape: 40
  • 41. Contextual Representations and Sequence Modeling • Recurrent neural networks are a type of neural network architecture that naturally handles modeling sequential data 41
  • 42. Contextual Representations and Sequence Modeling • This type of network generates a new output vector for each input in a sequence, and also feeds that same information forward 42
  • 43. Contextual Representations and Sequence Modeling • By feeding the information forward, each subsequent output vector has contextual information encoded from the preceding words 43
  • 44. Contextual Representations and Sequence Modeling • This type of architecture can be used to build language models, where the task is to predict the next word in the sequence 44
  • 45. Contextual Representations and Sequence Modeling • It can also be used for problems like named entity recognition 45 animalo o o o animal
  • 46. Contextual Representations and Sequence Modeling • By taking the final vector in the sequence, you can perform tasks like sentiment classification 46 positive
  • 47. Contextual Representations and Sequence Modeling • For all of these different types of tasks, a network similar to the perceptron can be placed at the end to carry out the final classification of each word 47
  • 48. Contextual Representations and Sequence Modeling • For all of these different types of tasks, a network similar to the perceptron can be placed at the end to carry out the final classification of each word, or the classification of the whole sequence 48
  • 49. Contextual Representations and Sequence Modeling • In a similar manner, these individual elements can be combined in a variety of ways to tackle very complex tasks 49
  • 50. Contextual Representations and Sequence Modeling • In a similar manner, these individual elements can be combined in a variety of ways to tackle very complex tasks 50
  • 51. Contextual Representations and Sequence Modeling • In a similar manner, these individual elements can be combined in a variety of ways to tackle very complex tasks 51
  • 52. Contextual Representations and Sequence Modeling • In a similar manner, these individual elements can be combined in a variety of ways to tackle very complex tasks 52