Skip to main content

Microsoft teaches AI to see the funny side of things

microsoft open sources graph engine microsoftlogo
Airbnb’s prescient artificial intelligence predicts the best time to rent out your pad. Google’s self-teaching computers speed up spam detection and translation. And Microsoft’s, apparently, knows when a joke’s funny. As part of a recent study, researchers at the Redmond-based company collaborated with New Yorker cartoon editor Bob Mankoff to imbue artificial intelligence with a sense of humor. The results are predictably fascinating.

Microsoft researcher Dafna Shahaf, who headed the study, began by attempting to convey to the AI linguistic hallmarks of comedy, like sarcasm and wordplay. Shahaf fed the program hundreds of old New Yorker captions and cartoons and, with the aid of crowdsourced workers from Amazon’s Mechanical Turk, painstakingly organized each by two categories: context and anomalies. The ‘context’ label described what was pictured — in an office setting, objects like “secretary” and “phone” — while ‘anomalies’ highlighted any potential source of humor — an unexpected “stairway” in said office, for example.

Shahaf then set the software loose at the offices of the New Yorker, tasking it with identifying (or trying to identify) the funniest cartoon captions among a week’s worth of reader submissions. The result? The AI and the editors agreed about 55.8 percent of the time, or on about 2,200 selections. That’s nothing to sneeze at, Shahaf told Bloomberg — on average, the AI saved Mankoff “about 50 percent of [the] workload.”

It isn’t difficult to imagine applications beyond editorial decision-making. The techniques might one day be used to improve Microsoft’s real-time translation efforts (such as Skype Translator), or, Eric Horvitz told Bloomberg, help flesh out the personalities of digital assistants like Siri and Cortana.

And Microsoft’s software isn’t the only AI humorist around, surprisingly. An Israeli student developed a system capable of recognizing “patronizing sounding semantics” and “slang words in phrases in text” by feeding it more than 5,000 Facebook posts. Hebrew University’s SASI, or Semi-supervised Algorithm for Sarcasm Identification, can recognize sarcastic sentences in product reviews. And a scientist at Purdue University has designed algorithms capable not only of identifying jokes, but explaining why a particular joke is funny.

But consistently hilarious robots are a ways off. While Microsoft’s AI found that brevity played best in the New Yorker’s caption section, a University of Michigan system favored downbeat punchlines. Reconciling the two — deriving an objective humor metric — will take a lot more algorithmic fine-tuning. “Computers can be a great aid,” Mankoff told Bloomberg, “[but] there are more things in humor and human beings than are dreamt of in even Microsoft’s algorithms.”

Editors' Recommendations

Kyle Wiggers
Former Digital Trends Contributor
Kyle Wiggers is a writer, Web designer, and podcaster with an acute interest in all things tech. When not reviewing gadgets…
Even Microsoft thinks ChatGPT needs to be regulated — here’s why
A MacBook Pro on a desk with ChatGPT's website showing on its display.

Artificial intelligence (AI) chatbots have been taking the world by storm, with the capabilities of Microsoft’s ChatGPT causing wonderment and fear in almost equal measure. But in an intriguing twist, even Microsoft is now calling on governments to take action and regulate AI before things spin dangerously out of control.

The appeal was made by BSA, a trade group representing numerous business software companies, including Microsoft, Adobe, Dropbox, IBM, and Zoom. According to CNBC, the group is advocating for the US government to integrate rules governing the use of AI into national privacy legislation.

Read more
Elon Musk threatens to sue Microsoft over AI training
tesla and spacex ceo elon musk stylized image

Shortly after reports emerged on Wednesday that Microsoft is about to remove Twitter from its ad platform, Twitter CEO Elon Musk fired back with the threat of a lawsuit, claiming the computer giant illegally used Twitter’s data, such as users’ tweets, to train its artificial intelligence (AI) tools.

“They trained illegally using Twitter data,” Musk tweeted, adding: “Lawsuit time.”

Read more
Bing Chat: how to use Microsoft’s own version of ChatGPT
Bing Chat shown on a laptop.

Bing Chat is Microsoft's answer to ChatGPT -- in fact, it's based on the same technology that makes OpenAI's chatbot run.

But Microsoft has a very different approach, integrating generative AI directly into its Edge web browser and Bing search engine. It's even coming to the entire suite of Office apps in the future. Here's how to sign up and use Bing Chat today.
How to get Bing Chat

Read more