Much Ado About AI: Why I Built a Tool to Modernize Shakespeare’s Verse

AI translations lack the beauty of Shakespeare’s verse in every sense. But they provide on-ramps to enjoy it.

There’s a good argument that Shakespeare is the world’s most popular author. About 90 percent of American schools assign Shakespeare to students. His work has been translated into more than 100 languages. Declare “To be or not to be,” and most will answer, “That is the question.” The Bard’s work is widely integrated across culture, education, and the modern English language. Despite this, people find Shakespeare hard. Some might even say too hard.

In a recent survey of 500 teachers, 56 percent said their students found Shakespeare difficult to read. Of these teachers, 60 percent said the Elizabethan language was the biggest obstacle for students reading the plays. The themes of love, betrayal, and ambition are timeless—but maybe Elizabethan English isn’t. For many first-time readers, Shakespeare’s plays are full of unfamiliar words, phrasing, and grammatical constructions.

AI generated image of William Shakespeare at a diner, from Pickaxe Project, creators of the Shakespeare Translator.
This illustration on the website for the Shakespeare Translator tool was made with the generative AI software Midjourney. A few creators from Pickaxe, the Shakespeare Translator parent company, riffed off one another’s concepts on a shared Midjourney server. The file was initiated with prompts (“William Shakespeare sitting at a crappy modern Denny’s diner,” as well as “Victorian painting,” “Studio Ghibli,” and others). The team then refined concepts to arrive at the final version.

This reported difficulty with the language shouldn’t be viewed as a problem with Shakespeare. Elizabethan English didn’t suddenly become dated in 2023. It’s been unfamiliar and antiquated to readers for many decades. But increasingly, the language is a barrier to new readers starting a love affair with the material.

Here, in my view, artificial intelligence (AI) offers a unique benefit: facilitating the reading experience of Shakespeare’s works. Large language models (LLMs: the AI systems that power popular products like ChatGPT) have exciting potential to help people read older texts with relative ease.

If you provide AI models with text, they can instantaneously synthesize, explain, and contextualize it. They offer definitions of words, historical context, and other details that might escape a modern reader. If you’re reading War and Peace and have a foggy sense of Russian history, running a passage through an AI model quickly provides bullet points on Napoleon’s invasion of Russia as well as definitions of period-specific terms.

Also read: Librarians Can Play a Key Role Implementing Artificial Intelligence in Schools

AI can also accurately paraphrase Elizabethan language into modern English so readers can understand any line of Shakespeare. This strategy isn’t intended as a substitute for reading the original text, but as a “reading copilot” on hand to help.

Bard-themed AI tools are gaining popularity. One I created, Shakespeare Translator, has been used by over 50,000 readers. These AI models aren’t deterministic systems with pre-written translations mapped to certain lines. Rather, the tools use LLMs to analyze the context and language patterns, providing modern interpretations.

Many are quick to critique AI-powered reading tools. The arguments essentially center on the idea that using AI waters down the joy and rewards of reading. But using AI isn’t about replacing reading. It’s about helping more people appreciate difficult material, more readily, and with fewer barriers to entry.

If we embrace the idea that encounters with great art are edifying, then we should embrace any tech that creates more opportunities for these encounters.

While many resources supply modern summaries of Shakespeare, or annotating or paraphrasing of plays, AI-powered tools are categorically different. The technology leverages a vast dataset and neural networks to generate these translations in real time. The translations are fast, flexible, and can be expanded on with follow-up questions that ask for more context or further explanation of a line. These translations aren’t predetermined, so students can run the same Shakespeare line multiple times and get slightly different paraphrasings. They can ask follow-up questions like, “Who was Macbeth speaking to when he said that?” and receive answers.

How useful are these translations? Are they accurate? Do they actually help students grasp the meaning of lines? Judge for yourself.

Here’s the original text of the famous Hamlet speech
“To be, or not to be, that is the question: Whether ’tis nobler in the mind to suffer the slings and arrows of outrageous fortune, or to take arms against a sea of troubles and by opposing end them. To die; to sleep; No more; and by a sleep to say we end the heart-ache and the thousand natural shocks that flesh is heir to.”

Run through a Shakespeare translation tool, this is paraphrased to
“The big question is whether it’s better to keep on living or to end it all. Is it nobler to endure the hardships and misfortunes that life throws at us, or to fight against all the problems that come our way and put an end to them? Death would mean eternal rest and therefore an escape from the pain and suffering that life brings us.”

Or consider this from Richard III
“Now is the winter of our discontent made glorious summer by this sun of York; And all the clouds that lour’d upon our house in the deep bosom of the ocean buried.”

Paraphrase
“Our unhappiness has now turned into joy due to the presence of the ruler from York; and all of our worries and troubles are now in the past.”

These translations lack the beauty and power of Shakespeare’s verse in every sense. But they elucidate the meaning and make one eager to revisit the original. In the end, Shakespeare’s wisdom remains untouched. Technology just provides more on-ramps to enjoy it.


Mike Gioia is a writer and AI specialist living in Los Angeles. He studied English literature at Stanford University and worked for several years in TV writers’ rooms.

Be the first reader to comment.

Comment Policy:
  • Be respectful, and do not attack the author, people mentioned in the article, or other commenters. Take on the idea, not the messenger.
  • Don't use obscene, profane, or vulgar language.
  • Stay on point. Comments that stray from the topic at hand may be deleted.
  • Comments may be republished in print, online, or other forms of media.
  • If you see something objectionable, please let us know. Once a comment has been flagged, a staff member will investigate.


RELATED 

ALREADY A SUBSCRIBER?

We are currently offering this content for free. Sign up now to activate your personal profile, where you can save articles for future viewing

ALREADY A SUBSCRIBER?