Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Like an AI Could Ever Spot Sarcasm

blogs.nvidia.com

Post reply on HN
Print view View original

51–60 of 109 posts

Re: Like an AI Could Ever Spot Sarcasm

#51

Post by com2kid »

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.

Looks good in Firefox on Windows. I'm not on a high DPI monitor, which can certainly mess things up.

Taking a screenshot and zooming in with a pixel grid, the 'i' on comedian is antialiased to 3 pixels in total wide, though the 2 on the side are very light. Firefox is 2 pixels wide, but both columns are dark. Chrome is also 2 pixels wide, but the columns are rather lightly colored.

(Windows' native font antialiasing is amazing, I'm sad all apps don't use it...)

Re: Like an AI Could Ever Spot Sarcasm

#52

Post by sidlls »

brisance wrote: post #50
mozumder wrote: post #35

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.

People didn’t expect to be humbled by a machine at the game of Go either. Yet here we are.

Apples and oranges comparison. Go is much closer to chess than it is to recognizing sarcasm.

Re: Like an AI Could Ever Spot Sarcasm

#53

Post by gowld »

cabalamat wrote: post #28

Sarcasm is almost certainly AI-complete. Consider this post: https://cabalamat.wordpress.com/2018/01/31/royal-mail-announ... which is pretty easy for a human to tell is sarcastic, but would be difficult for an AI unless it actually understood it.

Why? It has a few tell-tale word choices, and image recognition would indicate that the stamp images are "wrong" and/or correlated to humor memes.

Re: Like an AI Could Ever Spot Sarcasm

#54

Post by gowld »

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).

Even humans have great difficulty discerning sarcasm in text. Poe's law is the famous statement that sarcasm is not distinguishable once the Overton window is sufficiently wide.

Re: Like an AI Could Ever Spot Sarcasm

#55

Post by gowld »

laretluval wrote: post #48

The point of sarcasm is to hide your true intent except for people who are sufficiently aligned with you to be able to decode it correctly. If computers can decode sarcasm then it is not effective. Then sarcasm will evolve.

I trust many more details of the secrets of my life to computers than people. Computers are smarter than people in many areas, so sarcasm that only a computer recognizes is not a problem for sarcasm.

Re: Like an AI Could Ever Spot Sarcasm

#56

Post by gowld »

freeflight wrote: post #10
civilian wrote: post #4

Sarcasm is a great tool. But there are a couple of people I know who never turn off their "Sarcastic tone", and it becomes impossible to tell what's genuine and what's bullshit. I try to tell them that their noise-to-signal ratio is bad, but they um... react defensively.

It can be a coping mechanism for depressive people just like cynism, at least I know that it serves that function for me: Can't be straight up negative, for dragging the mood down, so I'll settle for some sarcasm.

You are likely not fooling anyone with your sarcasm.

Re: Like an AI Could Ever Spot Sarcasm

#57

Post by fellellor »

I have to note that often humans fail to detect sarcasm, and police forums with religious fervor demanding the application of those ridiculous "\s" tags wherever they be deemed necessary. Small wonder, why it would be difficult to catch in a program.

Re: Like an AI Could Ever Spot Sarcasm

#58

Post by brisance »

sidlls wrote: post #52
brisance wrote: post #50

Earlier quoted context omitted.

People didn’t expect to be humbled by a machine at the game of Go either. Yet here we are.

Apples and oranges comparison. Go is much closer to chess than it is to recognizing sarcasm.

It may appear to you to be the case, but DeepBlue used a tree search algorithm. AlphaGo was an ensemble method that was based on neural networks, just like how the researchers used to detect sarcasm (sequence to vector). Read the article!

Re: Like an AI Could Ever Spot Sarcasm

#59

Post by bcaulfield »

Stratoscope wrote: post #42
bcaulfield wrote: post #39

Earlier quoted context omitted.

Put it back in. We love sarcasm!

OK, chief! I even stepped it up and called it "scrawny text" for good measure. I am like a politician waffling and flip-flopping as the polling winds blow to and fro. Hmm... Chicken and waffles sounds pretty good right now!

Will look into changing that font up, many thanks for the feedback!
Post reply on HN