Poetic AI system pens Shakespeare-like sonnets
However, experts could still easily identify machine-generated poetry, and AI may have a long way to go before it can outdo Shakespeare, researchers said.
Could artificial intelligence (AI) write sonnets as good as the Bard? A poetry writing algorithm developed by scientists was able to fool people trying to distinguish between human- and bot-written verses nearly 50 percent of the time.
In some ways, the computer's verses were better than Shakespeare's. The rhymes and meter in the machine-generated poetry were more precise than in human-written poems.
"It's very easy for me to tell what's by a computer or not – ridiculously easy," said Adam Hammond, an assistant professor at the University of Toronto.
"We solved two out of four problems," Hammond says, referring to rhyme and meter.
"The other two are much harder: making something that's readable and something that can evoke emotion in a reader," he said.
Researchers trained a neural network using nearly 2,700 sonnets from a free digital library.
The computer uses three models - language, meter and rhyming - and probability to pick the right words for its poem. It produced quatrains, or four lines of verse, in iambic pentameter.
Most laymen could not tell that verses like this one were the work of a programmed poet: "With joyous gambols gay and still array/ No longer when he was, while in his day/ At first to pass in all delightful ways/ Around him, charming and of all his days."
However, Deep-speare didn't fool the expert. Hammond said it was easy to spot the computer's verses because they were often incoherent and contained grammatical errors like the one above: "he was."
As the further comfort to poets who worry about being replaced by AI, Hammond said there is much more to a sonnet that a computer can not imitate yet.
"Our results suggest that future research should look beyond meter and focus on improving readability," they said.
(This story has not been edited by Devdiscourse staff and is auto-generated from a syndicated feed.)