[squarebear]

Haha! Ok I see. Glad you are proud of your work.

[8pla.net]

I don't get this one.
In what way is Mitsuku related to your bot and
how did you get that I was proud of your bot's answer?

Lets pose this quoted post by the world champion, to the young child, ANN...

Code

Judge:
I don't get this one. In what way is Mitsuku related to your bot and 
how did you get that I was proud of your bot's answer?

Contestant:
Let me break it down: 

You said: I don't get this one.
You asked: In what way is Mitsuku related to your bot and 
how did you get that I was proud of your bot's answer?

My answer: DON'T THIS ONE

[squarebear]

Oh dear. That one didn't work out too well. How come you posted it?

No matter what I think of you personally, I would never discourage anyone from working on AI projects and am genuinely pleased that you are happy with your work.

The same question posed to Mitsuku:

Human: I don't get this one. In what way is Mitsuku related to your bot and how did you get that I was proud of your bot's answer?
Mitsuku: Me either. I don't know. I'm not really into that family tree type stuff.

[8pla.net]

Well, my analysis is that "DON'T THIS ONE" is an imperative sentence that is grammatically correct.  An imperative sentence is a command. In theory the command "DON'T THIS ONE" may be short for "DON'T [be proud of] THIS ONE". However, this is an unconfirmed hypothesis.

[squarebear]

I think that must be just you then. "Don't this one" doesn't make sense to me. Certainly adding your own words in there seems to be clutching at straws and it may be worth refining the process that produced this output.

My hypothesis is that it somehow mangled "I DON'T get THIS ONE" to produce the output and ignored the 2nd sentence altogther.

[8pla.net]

The goal is to automatically produce canned response quality, without the canned responses. I did run those preliminary results in question through an online grammar checker at: http://www.gingersoftware.com/grammarcheck .  The response is grammatically flawless.  The grammar check found zero errors and zero warnings. So, I am pleased with those preliminary results.  Perfect grammar supports ongoing training.

With that said, don't think for one moment that mistakes are not made, they certainly are made.

Here are some fair tests I just ran. They are fair because in each case the question asks directly about the statement made.

Code

Judge:
I thought the movie was good. 
What did I think about the movie?

Contestant:
Let me break it down: 

You said: I thought the movie was good.
You asked: What did I think about the movie?

My answer: WAS GOOD

Code

Judge:
England is faraway. How far is England?

Contestant:
Let me break it down: 

You said: England is faraway.
You asked: How far is England?

My answer: FARAWAY

Code

Judge:
The USA is nearby. How near is the USA?

Contestant:
Let me break it down: 

You said: The USA is nearby.
You asked: How near is the USA?

My answer: NEARBY

Can you think of any to run?  The correct format is, a sentence, followed by a question about that sentence.

[DemonRaven]

My brain likes to take vacations so at the moment i can't think of anything to add to what you are doing.

[8pla.net]

Thanks for your support, friend.   This is the type of help I need (the part that is underlined)...


ANN

Judge:
My friend likes to take vacations.  What does my friend do?

Contestant:
Let me break it down:

You said: My friend likes to take vacations.
You asked: What does my friend do?

My answer: LIKES TO TAKE VACATIONS

[DemonRaven]

lol i am not sure if you meant to do that after my post or not but i found it funny.

[Don Patrick]

I've been lurking this topic because I don't understand how neural nets work, but I think I've spotted an amusing pattern to these question-answer pairs that the neural net seems to adhere to. As I said I have no idea how it works but this would be my hypothesis:

From the statement, remove all words that re-occur in the question. The words that remain form the answer.

[Korrelan]

'don't this one'... gave it away

[squarebear]

I think you guys gave nailed it. I just tried "Bruce Wilcox will be interviewed on CNN, Thursday, January 22nd at 9PM. Where will Bruce Wilcox be interviewed?" which Tom says replied back with "INTERVIEW ON CNN THURSDAY JANUARY 22ND AT 9PM". This struck me as strange if all it was doing was removing duplicate words, as it changed INTERVIEWED to INTERVIEW.

The actual output is :

Judge:
Bruce Wilcox will be interviewed on CNN, Thursday, January 22nd at 9PM. Where will Bruce Wilcox be interviewed?

Contestant:
Let me break it down:

You said: Bruce Wilcox will be interviewed on CNN, Thursday, January 22nd at 9PM.
You asked: Where will Bruce Wilcox be interviewed?

My answer: ON CNN THURSDAY JANUARY 22ND AT 9PM"

So yes, I agree that it just appears to remove duplicate words after maybe doing a bit of pronoun swapping.

[8pla.net]

I've been lurking this topic because I don't understand how neural nets work, but I think I've spotted an amusing pattern to these question-answer pairs that the neural net seems to adhere to. As I said I have no idea how it works but this would be my hypothesis:

From the statement, remove all words that re-occur in the question. The words that remain form the answer.

Welcome Don!  It is nice to have a genuine genius join in on our discussion. Spotting patterns in a neural network is a wonderful subject. I would like to discuss it further.  Have you been able to spot any patterns in how iCub's artificial neural network handles commands to manipulate objects?  For your convenience, here is a reference to your post about iCub: here Thanks for posting that video!


Happy pattern spotting...

ANN

Judge:
I learnt your secret.  What did I learn?

Contestant:
Let me break it down:

You said: I learnt your secret.
You asked: What did I learn?

My answer: MY SECRET

You can test your hypotheses or any of these examples at: http://elizabot.com/ANN/contest .  At the same time you will be helping greatly in artificial neural network training.  Thanks for your support.

[squarebear]

Judge:
one two three four. two four?

Contestant:
Let me break it down:

You said: one two three four.
You asked: two four?

My answer: ONE THREE

[8pla.net]

Hey squarebear, I think young ANN likes you.   This is an early, limited alpha test being designed for Turing Test questions, like they have at the chatbot contests.  Can you please try some of those?