Scientists Develop AI Network Capable of Writing Poetry
Researchers at the University of Colorado (UC) - Colorado Springs and Drury University have recently developed a unique system that can produce creative poetry.
At first, Researcher Brendan Bena, from the Colorado University, wanted to look at creating a system that would attempt to mimic the emotions elicited through song lyrics. But, as most song lyrics are protected by copyright, Bena decided to develop a deep learning tool for poetry generation instead.
Rather than focusing on features such as the structure or rhythm of poetry, like most previous poetry generation studies, he and his colleague explored its more emotional and creative aspects, the German News Agency reported.
According to the Tech Xplore website, the research team fed the artificial neural network myriads of poetry verses from different sources and different emotion categories like joy, sadness, trust, and anger.
The network generated new fragments of text by modeling the style of language used in the data it's trained on.
The researchers asked human users to evaluate and to assess the quality of the verses it generated.
They found that it produced poems that effectively elicited sadness and joy 87.5% and 85% of the time, respectively.
"Our findings suggest that text can, in fact, be generated so that it elicits emotion in readers and that it can resemble the types of creativity that artists look to inject in their work. We hope that our study will open the door to future work in this area," Bena explains.
Researchers had previously developed techniques that can generate written or spoken language which have attracted considerable attention, particularly with the introduction of new voice assistants, robots and new interactive devices.