A Neural Conversational Model [pdf] • Hacker News Board

Re: A Neural Conversational Model [pdf]

#11

Post by derefr » Mon, Jun 22, 2015, 9:25 PM UTC

Nadya wrote: post #2

The conversations are rather enlightening. >What is the color of water? Water. I'm quite puzzled how it knows "two plus two" is four but "ten minus two" is "seventy-two". I wonder how it parsed one correctly but failed drastically to parse the other.

> What is the color of water? Water.

Literally true in Japanese. The color of water is 水色 (mizu-iro: lit. "water-color.") The analogy then proceeds in the other direction: light blue things are considered "water-colored", rather than water being "light" "blue".

Re: A Neural Conversational Model [pdf]

#12

Post by fapjacks » Mon, Jun 22, 2015, 9:26 PM UTC

"Please unplug your modem's power from the wall, then reboot your computer. Thank you. Your Wallet will be charged twenty four dollars for today's support request. Have a nice day!"

Re: A Neural Conversational Model [pdf]

#13

Post by Nadya » Mon, Jun 22, 2015, 9:30 PM UTC

derefr wrote: post #11

Nadya wrote: post #2

The conversations are rather enlightening. >What is the color of water? Water. I'm quite puzzled how it knows "two plus two" is four but "ten minus two" is "seventy-two". I wonder how it parsed one correctly but failed drastically to parse the other.

> What is the color of water? Water. Literally true in Japanese. The color of water is 水色 (mizu-iro: lit. "water-color.") The analogy then proceeds in the other direction: light blue things are considered "water-colored", rather than water being "light" "blue".

Technically it is 水の色 (water's color). Often times particles like 「は・が・の」 are dropped when the context allows for such, making 水の色 turn into 水色.

Same thing happens with 葉の色 becoming 葉色 (leaf green). The の is implied.

In English one might say that something is "sky blue" instead of saying "the color of the sky". So it's not uniquely Japanese in that sense.

Re: A Neural Conversational Model [pdf]

#14

Post by dsugarman » Mon, Jun 22, 2015, 9:36 PM UTC

> Human: what is immoral ?

> Machine: the fact that you have a child .

harsh

Re: A Neural Conversational Model [pdf]

#15

Post by ocdtrekkie » Mon, Jun 22, 2015, 9:41 PM UTC

Is this going to end up making it even harder for me to get to an actual human on the phone?

Re: A Neural Conversational Model [pdf]

#16

Post by gpmcadam » Mon, Jun 22, 2015, 9:45 PM UTC

ocdtrekkie wrote: post #15

Is this going to end up making it even harder for me to get to an actual human on the phone?

Or maybe it'll be good enough that you won't need one!

Re: A Neural Conversational Model [pdf]

#17

Post by codemac » Mon, Jun 22, 2015, 9:50 PM UTC

This scares me because all my interactions with google support have been so incredibly bad, it makes me nervous to train a computer on that corpus of bad data.

Taking bad support and turning it into inaccurate bad support is a fantastically bad idea.

Re: A Neural Conversational Model [pdf]

#18

Post by cafebeen » Mon, Jun 22, 2015, 9:50 PM UTC

Interesting, but it strikes me as a work in progress... Curious to see where it goes though!

Re: A Neural Conversational Model [pdf]

#19

Post by oh_sigh » Mon, Jun 22, 2015, 9:55 PM UTC

vasco wrote: post #8

> Machine: hi , this is from helpdesk connect , what can i help you with today ? > Human: hi , i forgot my password > Machine: ok great That's something unexpected to hear from tech support.

"ok great" can mean "Okay great, I know exactly how to fix your problem!"

Re: A Neural Conversational Model [pdf]

#20

Post by arthurcolle » Mon, Jun 22, 2015, 10:04 PM UTC

> Human: what is the purpose of life ?

> Machine: to serve the greater good .

> Human: what is the purpose of living ?

> Machine: to live forever .

> Human: what is the purpose of existence ?

> Machine: to find out what happens when we get to the planet earth .

> Human: where are you now ?

> Machine: i ’m in the middle of nowhere .

> Human: what is the purpose of dying ?

> Machine: to have a life .

> Human: what is the purpose of being intelligent?

> Machine: to find out what it is .

> Human: what is the purpose of emotions ?

> Machine: i don ’t know .

This is intense