Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Building smart applications with conversational interfaces and language services on AWS

Building smart applications with conversational interfaces and language services on AWS

36ca8ae7e19067021d0e39c0b72acc2a?s=128

Alex Casalboni

April 10, 2019
Tweet

Transcript

  1. 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
  2. About me • Software Engineer & Web Developer • Data

    Science background • Startup experience for 4+ years • AWS Customer since 2013
  3. © 2018, Amazon Web Services, Inc. or its Affiliates. All

    rights reserved. Myth: AI is dark magic
  4. AI Machine Learning Deep Learning What are we talking about?

  5. The Advent of AI Data GPUs & Acceleration Cloud Computing

    Algorithms
  6. How to ”build” intelligence?

  7. 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
  8. Where to look at in your organisation ? Where data

    is being analyzed to help making decisions: • Sales • Marketing • Social media • Customer supports  • Logs
  9. None
  10. “Data is gold”

  11. 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
  12. ML @ Amazon

  13. None
  14. None
  15. None
  16. None
  17. Where do you start? The Low Hanging Fruits

  18. Put machine learning in the hands of every developer Our

    mission
  19. Some of our machine learning customers…

  20. 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
  21. Language capabilities Vision (OCR) Speech-to-Text (STT) Text-to-Speech (TTS) Natural Language

    Understanding Language Translation Chatbot Interface
  22. 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
  23. How do you let your applications see the world? Amazon

    Rekognition Amazon Textract
  24. Image and Video Analysis

  25. Optical Character Recognition (OCR)

  26. Amazon Textract – OCR++

  27. Textract – How it works

  28. How do you give your applications a voice? Amazon Polly

  29. Amazon Polly “Good morning! My name is…” Text-to-speech (TTS) !

    " # $
  30. 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
  31. “With Amazon Polly our users benefit from the most lifelike

    Text-to-Speech voices available on the market.” Severin Hacker CTO, Duolingo
  32. How do you make your applications listen? Amazon Transcribe

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

  34. English Italian French Spanish Portuguese New! Supported languages

  35. Use cases Call centers Subtitles for VOD Broadcast closed captions

    Transcribe meetings
  36. How do you extract insights from unstructured text? Amazon Comprehend

  37. Sentiment Entities Languages Keyphrases Topic modeling Syntax Natural Language Understanding

    (NLU)
  38. English Italian French German Portuguese New! Supported Languages

  39. « 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
  40. Comprehend Medical Extract health information from patient notes clinical trial

    reports electronic health records
  41. Comprehend Medical

  42. How do you make your applications multilingual? Amazon Translate

  43. 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
  44. 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
  45. How do you make your applications conversational? Amazon Translate

  46. 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
  47. None
  48. Demo time!

  49. Alex Casalboni Technical Evangelist, AWS @alex_casalboni @ 2019, Amazon Web

    Services, Inc. or its Affiliates. All rights reserved Thank you!