Like an AI Could Ever Spot Sarcasm • Hacker News Board

Re: Like an AI Could Ever Spot Sarcasm

#31

Post by marcosdumay » Wed, Jan 31, 2018, 11:54 PM UTC

Stratoscope wrote: post #21

com2kid wrote: post #18

Earlier quoted context omitted.

It actually looks quite nice in Firefox, it is hard to read in Chrome though. Maybe they have the one last web design team that primarily tests in FF? :D

I'm curious which OS you're using. On Windows, it looks pretty much equally bad to my eyes in Chrome, Firefox, and Edge.

It's legible in my computer. Debian 8, with Firefox, no-script, and ublocker, with 24" screen and a forced minimum font size of something that I don't even remember.

Anything of those could be making it legible. I'd rather trust the opinion of somebody with a more standard system, and I doubt the GP is that somebody either.

Re: Like an AI Could Ever Spot Sarcasm

#32

Post by marcosdumay » Wed, Jan 31, 2018, 11:55 PM UTC

Stratoscope wrote: post #8

Like a human being could ever read that text. If you're having as much trouble reading it as I was, open the developer tools and on the body style, remove "DINPro" from the font-family, turn off the font-weight: 300 or change it to 400, and increase the font-size to 16px or whatever size you like. If the AIs ever do take over, my one request is that they use plenty of sarcasm when they talk about designers who think…

Sarcastic CSS is the current fashion.

Re: Like an AI Could Ever Spot Sarcasm

#33

Post by stochastic_monk » Wed, Jan 31, 2018, 11:55 PM UTC

Inherently ambiguous medium of hierarchical, ambiguous data requiring personal and situational context difficult to interpret.

Surprise! NLP is still hard... which is good news for anyone interested in understanding language, neural networks, o the human condition.

Re: Like an AI Could Ever Spot Sarcasm

#34

Post by hx2a » Wed, Jan 31, 2018, 11:56 PM UTC

If anyone is interested in studying sarcasm themselves, there is a dataset available:

A Large Self-Annotated Corpus for Sarcasm https://arxiv.org/abs/1704.05579

1.3 million sarcastic statements!

Re: Like an AI Could Ever Spot Sarcasm

#35

Post by mozumder » Thu, Feb 01, 2018, 12:00 AM UTC

If humans can’t identify sarcasm, why would you expect AI to?

It’s like expecting AI to read handwriting, when people can’t even do that 100% of the time.

Re: Like an AI Could Ever Spot Sarcasm

#36

Post by icebraining » Thu, Feb 01, 2018, 12:02 AM UTC

marcosdumay wrote: post #31

Stratoscope wrote: post #21

Earlier quoted context omitted.

I'm curious which OS you're using. On Windows, it looks pretty much equally bad to my eyes in Chrome, Firefox, and Edge.

It's legible in my computer. Debian 8, with Firefox, no-script, and ublocker, with 24" screen and a forced minimum font size of something that I don't even remember. Anything of those could be making it legible. I'd rather trust the opinion of somebody with a more standard system, and I doubt the GP is that somebody either.

It's the no-script. Allowing scripts loads a crappy font. Hurray for NoScript!

Re: Like an AI Could Ever Spot Sarcasm

#37

Post by Retra » Thu, Feb 01, 2018, 12:12 AM UTC

ACow_Adonis wrote: post #23

JoeAltmaier wrote: post #12

It's more than incongruity. Context is king. "I like being ignored" is sarcasm. But followed up with "No, really, I like being ignored. Its like a super power! I can ..." is serious (sort of).

And then you get people like me, where "I like being ignored" is not sarcasm, but a commentary/personality preference related to disliking a cultures obsession with fame and popularity and struggling to think of anything worse than being recognised/constantly under surveillance. As you said, context is everything. It is literally impossible to detect sarcasm reliably with only the sentence in which sarcasm is contain…

There's also a blurry line between sarcasm and lies. I'll often say things that are patently untrue to people with the expectation that they know the truth (and me) well enough to get that I'm not serious.

For instance, to my sister:

"I hate you." - sarcasm. "I've already told you many times that I hate you." - obvious lie, maybe sarcasm?

Re: Like an AI Could Ever Spot Sarcasm

#38

Post by taneq » Thu, Feb 01, 2018, 12:17 AM UTC

marcosdumay wrote: post #32

Stratoscope wrote: post #8

Like a human being could ever read that text. If you're having as much trouble reading it as I was, open the developer tools and on the body style, remove "DINPro" from the font-family, turn off the font-weight: 300 or change it to 400, and increase the font-size to 16px or whatever size you like. If the AIs ever do take over, my one request is that they use plenty of sarcasm when they talk about designers who think…

Sarcastic CSS is the current fashion.

Cascading Snarky Sarky.

Re: Like an AI Could Ever Spot Sarcasm

#39

Post by bcaulfield » Thu, Feb 01, 2018, 12:24 AM UTC

Stratoscope wrote: post #20

kalms wrote: post #15

Earlier quoted context omitted.

You even left a comment on the site writing that. Don't be an asshole.

Fair enough, I edited the comment I posted there to take out the sarcasm and just kept the note on how to make the page readable. OK now?

Put it back in. We love sarcasm!

Re: Like an AI Could Ever Spot Sarcasm

#40

Post by matte_black » Thu, Feb 01, 2018, 12:30 AM UTC

Yes, this is exactly what we need.