Looking forward to the age of artificial intelligence? Then your sex doll or car or central air system for your home is going to have to know when you're telling the truth or just being a jerk.
Because computers process verbal commands in a straightforward fashion and humans tend to use more sophisticated speech forms, employing slang or symbols to convey an idea can scramble their circuit boards. So an Israeli research team has developed a machine algorithm that can recognize sarcasm. Oh really?
SASI, the Semi-supervised Algorithm for Sarcasm Identification, can recognize sarcastic sentences in product reviews online with pretty astounding 77% precision. So much for your clever retorts to random products. To create such an algorithm, the team scanned 66,000 Amazon.com product reviews, with three different human annotators tagging sentences for sarcasm. The team then identified certain sarcastic patterns that emerged in the reviews and created a classification algorithm that puts each statement into a sarcastic class. Let's hope those geniuses understand true sarcasm.
The algorithms were then trained on that seed set of 80 sentences from the collection of reviews. The annotated sentences helped the algorithm learn what sorts of words and patterns distinguish sarcastic remarks. Soon they turned the algorithm loose on an evaluation set. Pattern evaluation efficiency scored accurately 81% of the time, while the overall precision of the pattern recognition/sarcasm categorizing algorithm was accurate in better than 3 in 4 instances.
So the next time you get mad at your malfunctioning printer, you may want to be nicer, because it may understand you.
Because computers process verbal commands in a straightforward fashion and humans tend to use more sophisticated speech forms, employing slang or symbols to convey an idea can scramble their circuit boards. So an Israeli research team has developed a machine algorithm that can recognize sarcasm. Oh really?SASI, the Semi-supervised Algorithm for Sarcasm Identification, can recognize sarcastic sentences in product reviews online with pretty astounding 77% precision. So much for your clever retorts to random products. To create such an algorithm, the team scanned 66,000 Amazon.com product reviews, with three different human annotators tagging sentences for sarcasm. The team then identified certain sarcastic patterns that emerged in the reviews and created a classification algorithm that puts each statement into a sarcastic class. Let's hope those geniuses understand true sarcasm.
The algorithms were then trained on that seed set of 80 sentences from the collection of reviews. The annotated sentences helped the algorithm learn what sorts of words and patterns distinguish sarcastic remarks. Soon they turned the algorithm loose on an evaluation set. Pattern evaluation efficiency scored accurately 81% of the time, while the overall precision of the pattern recognition/sarcasm categorizing algorithm was accurate in better than 3 in 4 instances.
So the next time you get mad at your malfunctioning printer, you may want to be nicer, because it may understand you.
No comments:
Post a Comment