full transcript

From the Ted Talk by Raphael Arar: How we can teach computers to make sense of our emotions

Unscramble the Blue Letters

I've been collaborating with a ceioatonvrsn analyst at the lab to try to help our AI systems hold more human-sounding conversations. This way, when you have an interaction with a chatbot on your phone or a voice-based system in the car, it sounds a little more hamun and less cold and disjointed. So I created a piece of art that tries to highlight the robotic, clunky interaction to help us uetsadrnnd, as designers, why it doesn't sound human yet and, well, what we can do about it. The pciee is caleld Bot to Bot and it puts one conversational system against another and then epesoxs it to the general pbiulc. And what ends up hnppnieag is that you get something that tries to mimic human conversation, but falls short. Sometimes it works and sometimes it gets into these, well, loops of misunderstanding. So even though the machine-to-machine conversation can make sense, grammatically and colloquially, it can still end up feeling cold and robotic. And despite checking all the boxes, the dialogue lacks soul and those one-off quirks that make each of us who we are.

Open Cloze

I've been collaborating with a ____________ analyst at the lab to try to help our AI systems hold more human-sounding conversations. This way, when you have an interaction with a chatbot on your phone or a voice-based system in the car, it sounds a little more _____ and less cold and disjointed. So I created a piece of art that tries to highlight the robotic, clunky interaction to help us __________, as designers, why it doesn't sound human yet and, well, what we can do about it. The _____ is ______ Bot to Bot and it puts one conversational system against another and then _______ it to the general ______. And what ends up _________ is that you get something that tries to mimic human conversation, but falls short. Sometimes it works and sometimes it gets into these, well, loops of misunderstanding. So even though the machine-to-machine conversation can make sense, grammatically and colloquially, it can still end up feeling cold and robotic. And despite checking all the boxes, the dialogue lacks soul and those one-off quirks that make each of us who we are.

Solution

  1. called
  2. human
  3. exposes
  4. conversation
  5. public
  6. piece
  7. happening
  8. understand

Original Text

I've been collaborating with a conversation analyst at the lab to try to help our AI systems hold more human-sounding conversations. This way, when you have an interaction with a chatbot on your phone or a voice-based system in the car, it sounds a little more human and less cold and disjointed. So I created a piece of art that tries to highlight the robotic, clunky interaction to help us understand, as designers, why it doesn't sound human yet and, well, what we can do about it. The piece is called Bot to Bot and it puts one conversational system against another and then exposes it to the general public. And what ends up happening is that you get something that tries to mimic human conversation, but falls short. Sometimes it works and sometimes it gets into these, well, loops of misunderstanding. So even though the machine-to-machine conversation can make sense, grammatically and colloquially, it can still end up feeling cold and robotic. And despite checking all the boxes, the dialogue lacks soul and those one-off quirks that make each of us who we are.

Frequently Occurring Word Combinations

ngrams of length 2

collocation frequency
artificial intelligence 3
hard time 2
nostalgia score 2
ai systems 2
human intuition 2

Important Words

  1. ai
  2. analyst
  3. art
  4. bot
  5. boxes
  6. called
  7. car
  8. chatbot
  9. checking
  10. clunky
  11. cold
  12. collaborating
  13. colloquially
  14. conversation
  15. conversational
  16. conversations
  17. created
  18. designers
  19. dialogue
  20. disjointed
  21. ends
  22. exposes
  23. falls
  24. feeling
  25. general
  26. grammatically
  27. happening
  28. highlight
  29. hold
  30. human
  31. interaction
  32. lab
  33. lacks
  34. loops
  35. mimic
  36. misunderstanding
  37. phone
  38. piece
  39. public
  40. puts
  41. quirks
  42. robotic
  43. sense
  44. short
  45. soul
  46. sound
  47. sounds
  48. system
  49. systems
  50. understand
  51. works