Slide 1

Slide 1 text

Alex Casalboni Technical Evangelist, AWS @alex_casalboni @ 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved Building smart applications with conversational interfaces and language services on AWS

Slide 2

Slide 2 text

About me • Software Engineer & Web Developer • Data Science background • Startup experience for 4+ years • AWS Customer since 2013

Slide 3

Slide 3 text

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Myth: AI is dark magic

Slide 4

Slide 4 text

AI Machine Learning Deep Learning What are we talking about?

Slide 5

Slide 5 text

The Advent of AI Data GPUs & Acceleration Cloud Computing Algorithms

Slide 6

Slide 6 text

How to ”build” intelligence?

Slide 7

Slide 7 text

Data Visualization & Analysis Business Problem – ML problem framing Data Collection Data Integration Data Preparation & Cleaning Feature Engineering Model Training & Parameter Tuning Model Evaluation Are Business Goals met? Model Deployment Monitoring & Debugging Yes No Data Augmentation Feature Augmentation The AI Process Re-training Predictions

Slide 8

Slide 8 text

Where to look at in your organisation ? Where data is being analyzed to help making decisions: • Sales • Marketing • Social media • Customer supports  • Logs

Slide 9

Slide 9 text

No content

Slide 10

Slide 10 text

“Data is gold”

Slide 11

Slide 11 text

Pro-tips Make it ridiculously easy to collect and store any type of data. One line of code should be all it takes for anyone in the company to start collecting and storing new data points Make data ingestion cheap and highly scalable with managed services such as Amazon Kinesis Make data aggregation and exploration easy and accessible to everyone with services such as Amazon Athena and Amazon Quicksight

Slide 12

Slide 12 text

ML @ Amazon

Slide 13

Slide 13 text

No content

Slide 14

Slide 14 text

No content

Slide 15

Slide 15 text

No content

Slide 16

Slide 16 text

No content

Slide 17

Slide 17 text

Where do you start? The Low Hanging Fruits

Slide 18

Slide 18 text

Put machine learning in the hands of every developer Our mission

Slide 19

Slide 19 text

Some of our machine learning customers…

Slide 20

Slide 20 text

M L F R A M E W O R K S & I N F R A S T R U C T U R E Amazon ML Stack A I S E R V I C E S R E K O G N I T I O N I M A G E P O L L Y T R A N S C R I B E T R A N S L A T E C O M P R E H E N D L E X R E K O G N I T I O N V I D E O Vision Speech Chatbots A M A Z O N S A G E M A K E R B U I L D T R A I N F O R E C A S T T E X T R A C T P E R S O N A L I Z E D E P L O Y M L O P S & A L G O S F r a m e w o r k s I n t e r f a c e s I n f r a s t r u c t u r e E C 2 P 3 & P 3 d n E C 2 C 5 F P G A s G R E E N G R A S S E L A S T I C I N F E R E N C E Language Forecasting Recommendations NEW NEW NEW NEW

Slide 21

Slide 21 text

Language capabilities Vision (OCR) Speech-to-Text (STT) Text-to-Speech (TTS) Natural Language Understanding Language Translation Chatbot Interface

Slide 22

Slide 22 text

Language capabilities on AWS Vision (OCR) Speech-to-Text (STT) Text-to-Speech (TTS) Natural Language Understanding Language Translation Chatbot Interface Amazon Rekognition & Textract Amazon Transcribe Amazon Polly Amazon Comprehend Amazon Translate Amazon Lex

Slide 23

Slide 23 text

How do you let your applications see the world? Amazon Rekognition Amazon Textract

Slide 24

Slide 24 text

Image and Video Analysis

Slide 25

Slide 25 text

Optical Character Recognition (OCR)

Slide 26

Slide 26 text

Amazon Textract – OCR++

Slide 27

Slide 27 text

Textract – How it works

Slide 28

Slide 28 text

How do you give your applications a voice? Amazon Polly

Slide 29

Slide 29 text

Amazon Polly “Good morning! My name is…” Text-to-speech (TTS) ! " # $

Slide 30

Slide 30 text

Polly • Content creation • Mobile & desktop applications • Internet of Things (IoT) • Education & e-learning • Telephony • Game development Use cases • 58 voices across 28 languages • Lip-syncing & text highlighting • Fine-grained voice control • Custom vocabularies • Available in 18 AWS Regions Key features

Slide 31

Slide 31 text

“With Amazon Polly our users benefit from the most lifelike Text-to-Speech voices available on the market.” Severin Hacker CTO, Duolingo

Slide 32

Slide 32 text

How do you make your applications listen? Amazon Transcribe

Slide 33

Slide 33 text

“Hi, how are you?” Amazon Transcribe Speech-to-text (STT)

Slide 34

Slide 34 text

English Italian French Spanish Portuguese New! Supported languages

Slide 35

Slide 35 text

Use cases Call centers Subtitles for VOD Broadcast closed captions Transcribe meetings

Slide 36

Slide 36 text

How do you extract insights from unstructured text? Amazon Comprehend

Slide 37

Slide 37 text

Sentiment Entities Languages Keyphrases Topic modeling Syntax Natural Language Understanding (NLU)

Slide 38

Slide 38 text

English Italian French German Portuguese New! Supported Languages

Slide 39

Slide 39 text

« Amazon Comprehend helps us analyze the key sentiments, objects, and geos in our 30 million plus reviews & testimonies. Now we are able to discover new insights into the unique experiences available at each property, so our customers can make the best decision possible for their travel.” Matt Fryer, VP and Chief Data Science Officer, Hotels.com

Slide 40

Slide 40 text

Comprehend Medical Extract health information from patient notes clinical trial reports electronic health records

Slide 41

Slide 41 text

Comprehend Medical

Slide 42

Slide 42 text

How do you make your applications multilingual? Amazon Translate

Slide 43

Slide 43 text

Supported languages Arabic Simplified Chinese French German Spanish Portuguese Japanese Traditional Chinese Italian Russian Turkish Czech (417 translation combinations) Danish Dutch Finnish Swedish Polish Hebrew

Slide 44

Slide 44 text

Think high volume and time-sensitive data Share of worldwide digital content Machine translation • User-authored content • Text Analytics • Real-time communication • Content discovery Post-edited machine translation • Legal documents • Healthcare documents • Advertising materials

Slide 45

Slide 45 text

How do you make your applications conversational? Amazon Translate

Slide 46

Slide 46 text

Amazon Lex End to End Speech to Intent ASR+NLU integrated into one API Dialog Management Native support & maintains context Text to Speech Amazon Polly integrated into API Business Logic Native integration with AWS Lambda Deployment One click deployment Security Encrypted data in transit & at rest Scale Completely managed service Analytics Monitor and improve End to End

Slide 47

Slide 47 text

No content

Slide 48

Slide 48 text

Demo time!

Slide 49

Slide 49 text

Alex Casalboni Technical Evangelist, AWS @alex_casalboni @ 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved Thank you!