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

ADDC 2018 - Cristina Santamarina: Humans vs Bots: Typos, Trolls and other challenges for NLP

ADDC 2018 - Cristina Santamarina: Humans vs Bots: Typos, Trolls and other challenges for NLP

Humans vs Bots explores the technical limitations of NLP in a world of high expectations.

A mix of faster computers, a more mature artificial intelligence field and the growing collaboration of technologists and humanists is shaping the new generation of conversational interfaces. How much magic is there really involved and where are we in the practice? How are real chatbots from real brands performing?

In this talk Cristina Santamarina will review the 10 most important natural language challenges she faces when designing conversational interfaces. From slang and typos to rants and trolls she will provide examples and propose dialogue design techniques that can help mitigate them.

More about the talk, authors & slides: https://addconf.com/2018/schedule/humans-vs-bots-typos-trolls-and-other-challenges-for-nlp/
Read about the conference: https://addconf.com

More Decks by ADDC - App Design & Development Conference

Other Decks in Technology

Transcript

  1. Humans vs Chatbots @CRISSANTAMARINA

  2. None
  3. None
  4. None
  5. None
  6. None
  7. None
  8. None
  9. @ tnpgram

  10. None
  11. None
  12. None
  13. None
  14. @ tnpgram

  15. None
  16. None
  17. None
  18. None
  19. None
  20. None
  21. None
  22. None
  23. None
  24. None
  25. FEATURES LANGUAGES SLANG MISTEAKS LONG INPUT EMPATHY CONTEXT ABBREVIATIONS TROLLS

    REFERENCES 10 COMMON CHALLENGES IN NLP CHATBOT PROJECTS @ tnpgram
  26. FEATURES

  27. None
  28. None
  29. None
  30. None
  31. Basic features What’s the single most important action your users

    want to complete using your bot? Surveys, workflow support, online shopping, daily news, storytelling… pick your most important features and polish them until they’re smooth 1 Navigation and Support Once the basics are ready, make your chatbot better. Reorient users to the happy path, answer FAQs about chatbots and navigation and get your users human help when the chatbot can’t handle the conversation alone. 2 Small talk If you have minimised errors now you can improve your chatbot with small talk, cultural references, answers to other questions… Learn from the input your chatbot can’t process to discover new features. 3
  32. None
  33. FEATURES • Have a purpose and focus • Build from

    the bottom up • Start stating your purpose and limitations • Help lost users discover features • Use buttons and rich elements as support • Don’t get trapped in small talk What to do about?
  34. LANGUAGES

  35. None
  36. None
  37. None
  38. LANGUAGES • Focus on your market • Use your tools

    right • Use the right tools What to do about?
  39. CONTEXT

  40. None
  41. None
  42. None
  43. None
  44. CONTEXT • Quick, simple • Diagram your processes and subprocesses

    • Use buttons and other rich elements • Use your tools right What to do about?
  45. LONG INPUT

  46. None
  47. LONG INPUT • Consider limiting input length • Most long

    inputs are trolls or lost users What to do about?
  48. EMPATHY

  49. None
  50. None
  51. EMPATHY • Do you really need pre-processing? • Pay attention

    to the most important keywords • Emojis are the way we express feelings online What to do about?
  52. SLANG

  53. None
  54. SLANG • Reconsider your need to accept slang input •

    Analyse the way your users talk • Don’t sound TOO cool What to do about ?
  55. MISTEAKS

  56. None
  57. None
  58. MISTEAKS • Think: how literate are your users? • Use

    quick replies! • There’s some magic involved in this • Be creative: Think of ways to mess up words • The Real World™ will help you get better What to do about?
  59. REFERENCES

  60. None
  61. None
  62. REFERENCES • Focus on the happy path • Analyse users

    to select important references • Be up to date with news and memes • Use references as a wow / PR effect What to do about?
  63. ABBREVIATIONS

  64. None
  65. ABBREVIATIONS • Add common abbreviations • Think of vertical-specific language

    • Train on demand What to do about?
  66. TROLLS

  67. TIME + WORDS = $$$

  68. TROLLS • Look for long conversations and long entries •

    Block recurring trolls • Use trolls to improve your sarcasm • Don’t let them distract you, always redirect! What to do about?
  69. None
  70. Learn. By. Experience

  71. FEATURES LANGUAGES SLANG MISTEAKS LONG INPUT EMPATHY CONTEXT ABBREVIATIONS TROLLS

    REFERENCES 10 COMMON CHALLENGES IN NLP CHATBOT PROJECTS @ tnpgram
  72. THANK YOU! Questions? @CRISSANTAMARINA CRISTINA@THENEONPROJECT.ORG