Tag Archives: joke formulas

Can a Computer Write a Joke?

Posted on by

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:

DeepQA flowchart

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.

How to Write a Joke

Posted on by

There are formulas for writing jokes. Experienced joke writers go through a systematic process to turn something like a news item into a sentence or two that will make people laugh.

You may have heard that “Writing is rewriting.” That describes only part of the process. Writing a joke is first thinking of what to write, then slapping together a rough draft, and only then rewriting to maximize the laugh.

Here’s the process I went through recently to write a joke for Twitter.

The idea for the joke starts with this news headline:

“Giant African Snails Seized at Los Angeles Airport”

I have an emotional reaction to the headline—“That’s weird”—which alerts me that the news item might be of general interest and worth exploring as a joke Topic.

Giant African snails at LAXThe news item also feels promising because it has two handles–“snail” and “Los Angeles”—each of which has several well-known associations. That means there’s a great chance I can create a solid Punch Line from the associations. “Snail” has associations like “slimy,” “slow,” and “French people eat them.” “Los Angeles” has associations like “smog,” “traffic,” and all the individual celebrities.

To generate a Punch Line I focus first on the well-known “snail” association “slow” and ask myself which slow people are commonly associated with Los Angeles. I can’t think of any only-in-LA slowpokes so I expand my list of associations to include workers in general.

DMV in Los Angeles

To spark ideas I Google “slow workers,” which reminds me of the DMV. Ah-ha! Now I have the basis of my Punch Line: I’ll link snails with DMV employees using their shared association “slow.” The result is this:

Partial Rough Draft: “Giant African snails were seized at Los Angeles Airport…workers at the DMV.”

To complete my rough draft I need an Angle that connects my Topic and Punch Line smoothly and efficiently. So I add an Angle that explains how the snails became workers at the DMV and get this:

Rough Draft: “Giant African snails were seized at Los Angeles Airport. Instead of destroying them, officials gave them jobs at the DMV.”

I use the word “officials” a lot in topical jokes. It suggests authority figures but isn’t specific enough to be distracting.

So that’s my rough draft. That was writing, wasn’t it? So much for writing being rewriting. Now comes the rewriting.

I add “live shipment” to clarify that these creatures are animate and could conceivably perform some kind of work. I add “67” because that detail from the news story subtly reinforces that this incident actually occurred. I remove “African” because it’s distractingly specific and unnecessary for the joke. I repeat “snails” in the Angle because it’s so crucial to making the Punch Line work. And this version results:

Version #2: “A live shipment of 67 giant snails was seized at Los Angeles Airport. Instead of destroying the snails, officials gave them jobs at the DMV.”

That version could still use a little tweaking. I backload the Topic, moving the most important elements closer to the Punch Line. I add “customs inspectors” to get rid of the passive voice and to clarify why the snails were seized and might be destroyed. And I get this final version:

Joe Toplyn's tweet about snails and the DMV

Abbreviating the name of the airport took the joke down to exactly 140 characters, Twitter’s limit. That meant I didn’t have to waste more time, and possibly weaken the joke, trimming it to fit.

Before posting the joke I subject it to some Comedy Quality Tests. One of the tests gives me pause: Is the joke too familiar? Is making fun of slow DMV employees similar to making fun of airline food–too hacky? I decide that the joke is so effective that the laugh will blow away any possible whiff of hackiness. Copy and paste to Twitter.

For more on how to write jokes and other short-form comedy, buy my book Comedy Writing for Late-Night TV.The book "Comedy Writing for Late-Night TV"