On: Like an AI Could Ever Spot Sarcasm

[sidlls]

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

[umanwizard → sidlls]

I’m not convinced.

Good computer chess play is based on a deterministic tree walking algorithm, something that’s been clearly in computers’ wheelhouse since forever.

Good computer go play is based on neural pattern recognition, which is also (probably) what human sarcasm detection is based on.

[Declanomous → umanwizard]

On the other hand, go operates in a much more finite universe than conversation does. You have 2 pieces, and a number of places to put them. You have a goal.

Conversation doesn't work like that, and takes a vast amount of information to understand whether someone is being sarcastic.

[brisance → Declanomous]

So you’re saying that the people cited in the article accomplished something more significant than the AlphaGo team…?

[TuringTest → brisance]

Probably not, because the approach taken in the paper is identifying a small set of patterns that are present in sarcasm, not fully understanding the meaning and context of why the sentence is sarcastic. It's a useful tool with pragmatic applications in online discourse analysis, but not a solved problem.

[Declanomous → brisance]

I'm just saying it's easier to make progress when your universe is easier to define.

[brisance → sidlls]

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!

[fyi1183 → brisance]

AlphaGo also uses a tree search algorithm.

Every tree search algorithm needs a guiding heuristic, and that's what AlphaGo replaces with a neural network.

So both DeepBlue and AlphaGo are fairly described as being based on tree search.