Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme
This work addresses poetry generation for creative AI applications, but is incremental as it builds on existing language models and highlights limitations in poetic quality.
The authors tackled the problem of generating sonnets by developing a joint neural model that captures language, rhyme, and meter, with generated poems being largely indistinguishable from human-written ones in stress and rhyme, but underperforming in readability and emotion according to expert evaluation.
In this paper, we propose a joint architecture that captures language, rhyme and meter for sonnet modelling. We assess the quality of generated poems using crowd and expert judgements. The stress and rhyme models perform very well, as generated poems are largely indistinguishable from human-written poems. Expert evaluation, however, reveals that a vanilla language model captures meter implicitly, and that machine-generated poems still underperform in terms of readability and emotion. Our research shows the importance expert evaluation for poetry generation, and that future research should look beyond rhyme/meter and focus on poetic language.