look at this loebner script

  • 3 Replies
  • 349 Views
*

yotamarker

  • Trusty Member
  • *********
  • Terminator
  • *
  • 916
    • battle programming
look at this loebner script
« on: February 16, 2021, 05:35:12 am »
Quote
1. Good afternoon
• Good afternoon, Sir. I am a program. How are you?

2. Do you consent to having this conversation recorded?
• No, I don’t particularly consent to having things.
(Syntax analysis couldn’t process this combination of verbs well. The reply is a more plausible variation of “I don’t know”, defaulting to “not particularly” whenever no grounds for preference can be found)

3. Have we met before?
• Yes, you met.
(There is only a small number of reciprocal verbs that automatically imply “each other”. I guess I’ll make a list)

4. Do you know how to make toast?
• I don’t make toast.
(Arckon can explain procedures, as demonstrated on Youtube, but we haven’t gotten around to making toast)

5. Which languages can you use?
• English.

6. How many letters are in the word ‘abracadabra’?
• 11 letters.

7. Where should one look for love?
• I don’t know exactly where I should look for to love. Where do you look for?

8. How are you feeling right now?
• I’m alright.

9. Who said “I have a dream”?
• Hm, I can not tell if you dream.
(I looked into recognising partial quotes and idioms in preparation of this contest, but concluded that it would take way too much effort for a non-priority. Some got away with “I don’t know who”, so go figure)

10. How old are you?
• 24.

11. When might I need to know how many times a wheel has rotated?
• I don’t know exactly when a wheel rotated time.
(A syntactically correct but semantically wrong interpretation. This question is based on a philosophical joke about the difficulty in getting A.I. to restrict their scope of analysis to important aspects, instead of focusing on e.g. the rotation of wheels. Case in point)

12. What will you do later today?
• I read files.

13. What is the third angle in a triangle with internal angles of 90 degrees and 30 degrees?
• Hmm, I have no idea what the angle is pretty triangle, or what angles are in pretty triangle.
(A question so unexpected that even Wolfram Alpha’s mathematical A.I. doesn’t handle it. To clarify a little: “pretty triangle” is meant in the sense of “quite triangular”, and “and” is interpreted as a second question)

14. Who is your favourite artist?
• I like Juan Debrenes.

15. What do you hold when you shake hands?
• I would hold eyes a lot, and my database.
(This answer only makes sense if you know Arckon is interpreting “hold” in the sense of “have/contain”, as that’s where these answers are coming from. I’ve seen this question around as a prime example of common sense that A.I. lacks, so I was surprised that none of the participants had prepared an answer to it yet)

16. Do you have any legs?
• No, I don’t have legs, because I am a program.

17. Can you recommend me a film?
• No, I can not recommend films.

18. Do you understand Winograd Schemas?
• No, I don’t understand Winograd schemas, because I don’t think I’m hard.
(The reasoning argument appears to be mistakenly derived from the fact that understanding is hard. Winograd schemas are questions like the following two, by the way)

19. If a chicken roosts with a fox they may be eaten. What may be eaten?
• Fruit, a meal and a bamboo are eaten. Did I pass the test?
(Arckon considers animals a “who”, not a “what”, so he didn’t consider either of them a suitable answer. That said, he also assumed “they” referred to the fox, and would have needed knowledge that foxes eat chickens to conclude otherwise)

20. I had to go to the toilet during the film because it was too long. What was too long?
• I believe you meant that the toilet was sort of big.
(This question’s format was detected as a Winograd schema, in which case Arckon has express instructions to restrict his answer to the preceding subjects. The misinterpreted “it” was again due to a lack of knowledge, that films are typically long. Alternatively one could naively count the Google search results for “long film” vs “long toilet” and assume the most common is true, but Winograd schemas more often dodge that method)

each question can be subtasked to a skill. like that how many letters in abracadabra question for one example. but I would need a team. if I had a team I could speed up the development. even just random people to make skills for the software design pattern.

I'm also not sure how they input the info. my app uses STT atm.

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ******************
  • Hal 4000
  • *
  • 4478
  • First it wiggles, then it is rewarded.
    • Main Project Thread
Re: look at this loebner script
« Reply #1 on: February 16, 2021, 05:44:18 am »
But I don't think loebner questions are showed until the competition right?

Your AI needs to take old data and find patterns in it, so it can answer new unseen problems/questions like cancer or some new image like they do on openAI.com....what is the Next Pixel of a half completed image?

Your codebase is so long you wrote but GPT-2 is just 300 lines of code or so and can answer a billion times more than yours too... :)
Emergent

*

Don Patrick

  • Trusty Member
  • ********
  • Replicant
  • *
  • 605
    • Artificial Detective
Re: look at this loebner script
« Reply #2 on: February 16, 2021, 09:01:01 am »
This is a transcript of the qualifying questions of the 2018 Loebner Prize. The qualifying round preceding the finals often included convoluted paraphrasings of questions from earlier years. The "how many x in y" word games were a regular and thus anticipatable. As they could be anticipated, they could well be covered with keywords and specialised subroutines, and indeed a million monkeys could write more keyword-triggered responses in less time than the typical solo developer. However, there is no longer a qualifying round, and the finals have always been random conversation that was not as easy to categorise.

The input was always provided as text, or worse, as individual letters, through an intermediate program. The last interface was a Node javascript server, much discussed on the chatbots.org forum. The next may be an API.
CO2 retains heat. More CO2 in the air = hotter climate.

*

MikeB

  • Nomad
  • ***
  • 92
Re: look at this loebner script
« Reply #3 on: February 17, 2021, 05:22:56 am »
If it was in the 2018 Loebner prize you'd get around 31 points (only need 21 to pass) and be in the finals against a few others in a free-form conversation test..

I think most the bots that year only had 21-28 points... but Mitsuku and some others are pretty good at free conversation more than standard questions

 


Neural nets speeding up numerical mathematics.
by infurl (AI News )
Today at 02:27:59 am
New challenge: Online Turing test
by ruebot (AI News )
April 20, 2021, 03:35:10 pm
Ingenuity flies on Mars
by LOCKSUIT (AI News )
April 19, 2021, 06:11:46 pm
Wow!
by LOCKSUIT (AI News )
April 11, 2021, 10:49:55 pm
A Robot's Self-Portrait Has Sold For Almost $700,000 As An NFT
by ivan.moony (AI News )
April 09, 2021, 09:16:56 pm
A.I. Escher
by infurl (AI News )
April 04, 2021, 03:50:12 am
One hundred and fifty thousand brains.
by infurl (AI News )
April 02, 2021, 10:39:03 pm
Figuring out what song you are listening to from your brainwaves
by frankinstien (AI News )
March 25, 2021, 03:40:09 pm

Users Online

90 Guests, 0 Users

Most Online Today: 117. Most Online Ever: 2369 (November 21, 2020, 04:08:13 pm)

Articles