Joe Toplyn

  • Home
  • About
  • Blog
  • Galleries
    • “Late Night with David Letterman”
    • “The Tonight Show with Jay Leno”
    • “Monk”
  • Events
  • Media Page
  • Contact

Can a Computer Write a Joke?

Posted on May 5, 2016 by Joe Toplyn

Before long, computers will be writing jokes as funny as those created by professional comedy writers.

 

3d2I’m no expert in computational humor, but I am the author of “Comedy Writing for Late-Night TV.” It’s possibly the most practical guide to writing jokes and other short-form comedy ever written.

 

I’ve also been reading up on the rapid advances in artificial intelligence (AI).

 

Take a look at these AI milestones:

 

IBM's Deep Blue vs. Gary Kasparov1997: IBM’s Deep Blue computer system beats a human world champion in a chess match.

 

2011: IBM’s Watson computer system beats human champions in Jeopardy.

 

2016: Google’s AlphaGo computer program beats a top-ranked human in Go.

 

Each of those milestones was previously considered unattainable by a computer. Each of them was considered to be a true test of a computer’s ability to think like a human. And a computer raced past each one of them.

 

The ability to write a good joke will be the next barrier for AI that a computer leaps over. That’s because writing a joke involves executing the kind of algorithms that computers can apparently already execute.

 

Here’s how I believe a computer system like IBM’s Watson will soon be able to write a joke.  (What I know about Watson I get from The AI Behind Watson: The Technical Article.)
Senior citizen with personal robot

 

Say you’re a senior citizen sitting at home with no one but your personal robot for companionship. You’re reading the news and you say, “Huh.  Some airline employee was arrested with over two hundred eighty two thousand dollars in his backpack.”

 

In a flash, the computer brain in your robot companion takes these steps:

 

STEP 1: The computer identifies the most unusual keywords and sentence fragments in the potential joke topic you uttered. Those are the linguistic elements–I call them handles–that made the topic interesting enough for you to comment on.

 

This process of parsing the joke topic into handles seems similar to what IBM’s Watson did every time it “decomposed” a Jeopardy question into “subclues.”

 

In our hypothetical joke topic, the two handles are “airline employee” and “two hundred eighty two thousand dollars.”

 

STEP 2: For each of those two handles, the computer generates a list of what I call associations. An association is a word or phrase that’s somehow related to the handle.

 

airport restaurant

One association of “airline employee” is “airport restaurant,” which has the sub-association “costs a lot of money.”

 

And one association of “two hundred eighty two thousand dollars” is “a lot of money.”

 

This process of generating associations seems similar to what IBM’s Watson did when it found phrases that were statistically related to keywords by using its “hypothesis generation” algorithms.

 

STEP 3: The computer makes a connection between the two associations “costs a lot of money” and “a lot of money” and it decides to build a punch line around that strong connection.

 

This process seems similar to what IBM’s Watson did when it evaluated candidate Jeopardy answers by using its “evidence retrieval” algorithms.

Here’s a diagram of Watson’s question-answering (QA) architecture:

STEP 4: The computer uses its automated reasoning skills to devise what I call an angle leading from the joke topic to the punch line. The computer might reason this way: The airline employee has a lot of money, so he can dine at an airport restaurant, which costs a lot of money.

 

STEP 5: The computer uses its natural language generation (NLG) skills to transform the topic-angle-punch line data of the candidate joke into conversational English.

 

Some NLG systems are currently used to transform numerical data into sentences in English. And other computer programs known as chatbots now use NLG systems to simulate human conversation.

 

STEP 6: The computer decides that the resulting candidate joke is probably surprising enough to be funny. It does this by searching through its store of human knowledge and finding that a meal at an airport restaurant is extremely unlikely to cost two hundred eighty two thousand dollars.

 

This process seems similar to what IBM’s Watson did when it performed “confidence estimation” and “ranking” on a candidate answer.

 

STEP 7: The computer directs your robot companion to tell you the joke.

 

Sure, those are a lot of steps for a computer to execute. But remember, IBM’s Watson beat human champions in Jeopardy. That strongly suggests that a computer could do all of the above really fast, as fast as a professional comedian.

 

And it may be even easier for a computer to get a laugh than to win dollars in Jeopardy. That’s because there is only one way to win a Jeopardy question: figure out the one correct answer and buzz in first.

 

But there are several ways to get a laugh from any given joke topic. A fertile joke topic–one with a lot of associations–may spawn three or more different jokes. And those jokes don’t have to be of professional quality to get a laugh; they just have to be reasonably funny.

Man in airport restaurant
So when you comment to your robot companion, “Look at this. Some airline employee was arrested with over two hundred eighty two thousand dollars in his backpack,” the robot might wisecrack:

“He probably needed the money to buy lunch at the airport.”

And you, the senior citizen, might chuckle and feel a little less lonely.

 

High-quality computational humor is the next Holy Grail for AI. That’s because a computer with a sense of humor is a more human computer. And a more human computer is worth billions of dollars.

 

The book "Comedy Writing for Late-Night TV"Help maintain humanity’s lead in comedy writing! Get my book “Comedy Writing for Late-Night TV.”

 

UPDATE :

Soon after I wrote the above post I decided to dust off my engineering degree and teach a computer to be funny myself.

I learned how to program in Python and how to use many readily-available tools of natural language processing (NLP), natural language generation (NLG), and machine learning (ML).

Then I used those tools to transform some of the techniques in my book, “Comedy Writing for Late-Night TV,” into computer code.

Now I think it’s fair to update the second paragraph of my original post to say that I am an expert in computational humor.

I also think it’s fair to answer the question posed by the title of my original post this way: Yes, a computer can write a joke.

I call my joke-writing software Witscript (U.S. Patent Nos. 10,642,939; 10,878,817; and 11,080,485). Right now the jokes it makes aren’t very sophisticated.

But as research in artificial general intelligence (AGI) advances, Witscript can learn to create smarter jokes. Witscript is a road map to a computer with a sense of humor, like a witty human companion.

Witscript also represents a new approach to computational creativity.

On November 22, 2019, I presented a poster about Witscript at the Natural Language, Dialog and Speech (NDS) Symposium in New York City.

The poster is here.

And below is the poster abstract. For a demo of Witscript, contact me through my company website.

Witscript: Computational Methods for Generating Contextually Integrated Jokes
Joseph E. Toplyn, SB, Twenty Lane Media, LLC

Research shows that people prefer to interact with an artificial intelligence (AI) that exhibits a sense of humor. But most conversational AIs have only a limited ability to make jokes. For example, they only output jokes written by humans, they mostly generate nonsense that requires human editing, they only tell jokes on request, or they tell jokes unrelated to a context. In contrast, we present Witscript, a novel approach to computational humor that independently generates original, contextually integrated jokes. A user inputs text, which may be an utterance in dialog, into the Witscript system. Witscript uses natural language processing tools and word embeddings to identify which pair of keywords in the input text is most likely to be useful in creating a joke response. Word embeddings are then used to list words associated with each of the two keywords. The two word associations that have the best wordplay are linked to create a punch line. Finally Witscript uses a language model fine-tuned on a dataset of jokes to fill the gap between the input text and the punch line with bridge text in a natural-sounding way. This bridge text and the punch line comprise a joke response to the original input text. The system outputs the joke response to the user only if it exceeds a preset score. With Witscript software to simulate a humanlike sense of humor in conversation, chatbots can be more engaging and personal robots can be friendlier companions.

Posted in Writing Tips | Tags: can a computer be funny, can AI understand jokes, can an AI recognize humor, can an artificial intelligence understand jokes, can computers be funny, can computers be taught to be funny, can computers create humor, can computers have a sense of humor, Can computers learn to be funny, can computers tell jokes, Can robots be funny?, Can you teach a computer to be funny?, can you teach humor to an AI, comedy algorithms, computational creativity, computational humor, funny robot, humor generation, joke algorithms, joke formulas, joke generation, joke-telling robot, machine joking, natural language generation, robot telling jokes, will artificial intelligences have a sense of humor, Witscript | 2 Comments
« Writing for Late-Night TV: A Panel Discussion
Joke About Earls restaurant and High Chairs »

2 thoughts on “Can a Computer Write a Joke?”

  1. Wayne says:
    December 28, 2020 at 3:22 pm

    Association jokes are more complex.
    Even easier for automation is sarcasm and insults.
    A bank computer asks a yes no question.
    “Here for banking?”
    YES. Computer says “Well duh.”
    NO Computer says “First day on the internet?”
    NO ANSWER “Are yes no quesitons too challenging?”

    Reply
    • Joe Toplyn says:
      January 12, 2021 at 8:03 pm

      Wayne, those are funny jokes.

      Yes, one way to get chatbots to crack jokes is to have humans write the jokes ahead of time, and also write rules that control when the chatbot will crack each pre-scripted joke. That approach gives the chatbot administrator total control over what the chatbot says in any given situation.

      But that approach also limits the number of jokes that the chatbot can utter without repeating itself. It also requires that humans keep writing new jokes to keep the chatbot’s sense of humor up-to-date.

      Witscript takes a different approach. Witscript lets a chatbot improvise original joke responses on the spot, instead of just retrieving canned joke responses from a database.

      I think Witscript’s approach is better for chit-chat chatbots because it creates new jokes on the fly the way a witty human does, which gives it more flexibility.

      Right now Witscript’s jokes are based on wordplay. But the same basic architecture will allow it to make more sophisticated associations and jokes as artificial intelligence tools improve.

      Reply

Leave a comment Cancel reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Sign up to get more tips and offers from Joe.

Joe’s Tweets

Joe Toplyn 2 days ago

The search warrant for former President Trump's Mar-a-Lago home shows that the FBI recovered 11 sets of classified documents. In his defense, Trump said that "classified documents" means that he "made the documents classy."

Joe Toplyn 3 days ago

Today in Germany, 31 people were injured on a roller coaster at a Legoland amusement park. But everybody’s okay because park officials quickly took the roller coaster apart and used the pieces to build a hospital.

Joe Toplyn 4 days ago

A Kansas man convicted of performing illegal autopsies has been fined more than $700,000. $700,000 for illegal autopsies! That’s a stiff punishment.

Joe Toplyn 5 days ago

Today the FBI executed a search warrant at former President Trump's home, Mar-a-Lago. Some good news for Trump, though: they actually found those 11,000 votes he was looking for in Georgia.

Joe Toplyn 6 days ago

The Casper mattress company is looking to hire people with "exceptional sleeping ability" to demonstrate its mattresses. "Exceptional sleeping ability"...so basically they're looking for people who don't watch the news.

Joe Toplyn 6 days ago

A CDC study said that last summer dozens of people got sick from bacteria and the norovirus at a splash park in Kansas. But splash park officials say the water is safe this year because heat waves and global warming boiled it.

Joe Toplyn 1 week ago

Fashion company Balenciaga is selling the world's most expensive garbage bag; it costs almost $1,800. So finally lazy people can have the perfect excuse not to take out the trash.

Categories

Pages

  • About Joe
  • Blog
  • Contact
  • Events
  • Media Page
  • Photo Galleries
    • “Late Night with David Letterman”
    • “Monk”
    • “The Tonight Show with Jay Leno”

Recent Posts

  • Joke About Kissing Poultry July 25, 2022
  • Joke About the Fourth of July July 4, 2022
  • Joke About Revlon’s Bankruptcy June 20, 2022
  • Joke About the Series “Obi-Wan Kenobi” June 6, 2022
  • Joke About Overpriced Beer May 23, 2022

Pages

  • About Joe
  • Blog
  • Contact
  • Events
  • Media Page
  • Photo Galleries
    • “Late Night with David Letterman”
    • “Monk”
    • “The Tonight Show with Jay Leno”

Archives

  • July 2022
  • June 2022
  • May 2022
  • April 2022
  • March 2022
  • February 2022
  • January 2022
  • December 2021
  • November 2021
  • October 2021
  • September 2021
  • August 2021
  • July 2021
  • June 2021
  • May 2021
  • April 2021
  • March 2021
  • February 2021
  • January 2021
  • December 2020
  • November 2020
  • October 2020
  • September 2020
  • August 2020
  • July 2020
  • June 2020
  • May 2020
  • April 2020
  • March 2020
  • February 2020
  • January 2020
  • December 2019
  • November 2019
  • October 2019
  • September 2019
  • August 2019
  • July 2019
  • June 2019
  • May 2019
  • April 2019
  • March 2019
  • February 2019
  • January 2019
  • December 2018
  • November 2018
  • October 2018
  • September 2018
  • August 2018
  • July 2018
  • June 2018
  • May 2018
  • April 2018
  • March 2018
  • February 2018
  • January 2018
  • December 2017
  • November 2017
  • October 2017
  • September 2017
  • August 2017
  • July 2017
  • June 2017
  • May 2017
  • April 2017
  • March 2017
  • February 2017
  • January 2017
  • December 2016
  • November 2016
  • October 2016
  • September 2016
  • August 2016
  • July 2016
  • June 2016
  • May 2016
  • April 2016
  • March 2016
  • February 2016
  • January 2016
  • December 2015
  • November 2015
  • October 2015
  • February 2015
  • November 2014
  • October 2014
  • September 2014
  • August 2014
  • July 2014
  • June 2014
  • April 2014
  • March 2014

Categories

  • Joke Writing Workshop (349)
  • Late-Night Writing (13)
  • Writing Tips (12)

WordPress

  • Log in
  • WordPress

CyberChimps WordPress Themes

© 2014 Joe Toplyn. All Rights Reserved.