Re:Like an AI Could Ever Spot Sarcasm
by jboggan on Wednesday January 31, 2018 @05:29PM
(#16278122)
Last year we were working on a rubber ducky debugging chatbot and relying a bit too heavily on StackOverflow data for conversational training data. It frequently gave sarcastic answers, especially if you asked for help concerning regular expressions.
[ Parent
| on HN ]
Re:Like an AI Could Ever Spot Sarcasm
by colejohnson66 on Thursday February 01, 2018 @01:07AM
(#16279903)
Did it respond with Zalgo if you asked about Regex and HTML? https://stackoverflow.com/questions/1732348/regex-match-open...
He comes.
Name the bot Tony the Pony and call it a feature.
Is there an online demo? Or a recording? Would love to see it! And how did you get the data? Is there a public dataset or did you crawl on your own?
Re:Like an AI Could Ever Spot Sarcasm
by JamieBeckett on Thursday February 01, 2018 @04:33PM
(#16286121)
The researchers had something online at one point, but it wasn't working when I needed the link for the story. They said they planned to fix it, but so far they haven't.
"Use jQuery"
Re:Like an AI Could Ever Spot Sarcasm
by golergka on Thursday February 01, 2018 @03:46AM
(#16280431)
That sounds like a pretty good result. Yandex has released it's voice assistant a few months ago (wasn't big news here on HN because it's Russian-only), and one feature that separated it from all the rest was sarcasm and kind of dark humor it acquired. Wouldn't you want your chatbot to be sarcastic sometimes?