Rasa AI: Building clever chatbots

Slides from a talk about rasa AI at the wearedevelopers conference vienna in may 2017

Transcript

1. Conversational AI:
   Building clever chatbots
   Tom Bocklisch, Lead ML Engineer @ LASTMILE
   

   View Slide

2. Example of a live Skill:
   A customer can change
   her address via
   Facebook Messenger
   Conversational AI will
   dramatically change
   how your users
   interact with you.
   

   View Slide

3. An open source, highly scalable ML
   framework to build
   conversational software
   

   View Slide

4. is a technology company developing conversational AI.
   Goal: next-generation intelligent bots
   Team: tight-knit, fast-moving team of researchers,
   engineers, designers and product people
   Location: everywhere (honestly: Berlin, Edinburgh, Beijing)
   We work on the core technology for next-generation conversational AI
   Founders:
   Dr. Alan Nichol (CTO)
   Alexander Weidauer (CEO)
   Advisory Board:
   Chad Fowler (MD & CTO @ Wunderlist)
   Matthaus Krzykowski (former Co-Founder @ Xyo)
   Cat Noone (Designer & Founder @ Iris)
   Investors: Reference customers:
   Introduction
   

   View Slide

5. Architectural Overview
   Introduction
   AI
   (Natural Dialogue
   Management)
   (Natural Language
   Understanding)
   (Natural Language
   Generation)
   (Conversational
   Platform, e.g.
   Facebook
   Messenger)
   “What’s the weather
   like tomorrow?”
   (User Request via text or voice)
   “It will be sunny and
   20°C.”
   (AI response via text or voice)
   (Your backend,
   database or API)
   

   View Slide

6. Under The Hood
   

   View Slide

7. Natural Language Understanding
   Natural Language
   Understanding
   What’s the
   weather like
   tomorrow?
   Example Entity Extraction Pipeline
   ”What’s the weather like tomorrow?” { “date”: “tomorrow” }
   Tokenizer
   Part of Speech
   Tagger
   Chunker
   Named Entity
   Recognition
   Entity Extraction
   Example Intent Classification Pipeline
   ”What’s the weather like tomorrow?” { “intent”: “request_weather” }
   Vectorization Intent Classification
   Under The Hood
   

   View Slide

8. Demo
   

   View Slide

9. 1. Create your training data
   Demo
   E.g. using the contributed rasa NLU gui at
   https://golastmile.github.io/rasa-nlu-trainer/
   

   View Slide

10. 2. Configure the model
    Configure the
    model
    Demo
    

    View Slide

11. 3. Train
    Training the
    model
    Demo
    

    View Slide

12. 4. Use Model
    Playing around
    with the trained
    model
    Demo
    

    View Slide

13. Under The Hood
    

    View Slide

14. Dialogue Handling
    Under The Hood
    “What’s the weather
    like tomorrow?”
    Intent
    Entities
    next
    Action
    State
    previous
    Action
    “Thanks.”
    after next
    Action
    updated
    State
    “It will be sunny
    and 20°C.”
    SVM
    Recurrent NN
    ...
    

    View Slide

15. Detailed Dialogue Handling
    Under The Hood
    “What’s the weather
    like tomorrow?”
    “It will be sunny and
    20°C.”
    Entity
    Input
    Action Mask
    Renormal-
    ization
    Sample
    action
    Action
    type?
    Response
    API Call
    Recurrent
    NN
    API Call
    Entity
    Output
    Intent
    Classification
    Entity
    Extraction
    Similar to LSTM-dialogue prediction paper: https://arxiv.org/abs/1606.01269
    

    View Slide

16. Final Thoughts
    

    View Slide

17. Open Challenges
    Final Thoughts
    Challenges for curious minds:
    ●
    ● Unsupervised multi-language entity recognition
    ● Dialogue generalisation (e.g. optional questions)
    Chit-Chat
    model
    Task-Oriented
    model
    I want to travel
    to Spain.
    ?
    ● Combination of different dialogue models
    

    View Slide

18. Current Research
    Final Thoughts
    Good reads for a rainy day:
    ● Last Words: Computational Linguistics and Deep Learning (blog)
    https://goo.gl/lGSRuj
    ● Memory Networks (paper)
    https://arxiv.org/pdf/1410.3916
    ● End-to-End dialogue system using RNN (paper)
    https://arxiv.org/pdf/1604.04562.pdf
    ● MemN2N in python (github)
    https://github.com/vinhkhuc/MemN2N-babi-python
    

    View Slide

19. ● Conversational AI is a big part of the future
    ● Deep ML techniques help advance state of the art NLU
    and conversational AI
    ● Open source is strategically important for enterprises
    implementing AI
    Summary
    Final Thoughts
    3 take home thoughts:
    

    View Slide

20. Get in
    touch!
    Tom Bocklisch
    Lead ML Engineer
    tom@golastmile.com
    

    View Slide