Deccan Chronicle

Poetic AI system pens Bard-like sonnets, almost

Scientists design logarithm that writes poetry following rules of rhyme, metre

-

Toronto, Aug. 9: 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 per cent of the time.

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.

Computer scientists at University of Melbourne in Australia and University of Toronto in Canada designed an algorithm that writes poetry following the rules of rhyme and metre.

In some ways, the computer’s verses were better than Shakespear­e’s. The rhymes and metre in the machine-generated poetry were more precise than in human-written poems.

The best version of the algorithm fooled people nearly 50 per cent of the time.

However ‘Deep-speare’ still has a long way to go before it writes anything worthy of the Western canon, researcher­s said.

“It's very easy for me to tell what’s by a computer or not ridiculous­ly easy,” said Adam Hammond, an assistant professor at University of Toronto.

Researcher­s trained a neural network using nearly 2,700 sonnets from a free digital library.

The computer uses three models - language, metre and rhyming - and probabilit­y to pick the right words for its poem. It produced quatrains, or four lines of verse, in iambic pentameter.

The researcher­s assessed their results by asking people online to tell the human and algorithm poetry apart.

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 twas, while in his day/ At first to pass in all delightful ways/ Around him, charming and of all his days.” However, Deepspeare 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 twas.” —

MOST LAYMEN could not tell the verses were work of a programmed poet.

EXPERTS easily identified machinegen­erated poetry as they were often incoherent and had grammatica­l errors.

 ??  ?? ‘DEEP SPEARE’ used three models - language, metre, rhyming - and probabilit­y to pick the right words.
‘DEEP SPEARE’ used three models - language, metre, rhyming - and probabilit­y to pick the right words.

Newspapers in English

Newspapers from India