Shall I Compare Thee to a Machine-Written Sonnet? An Approach to Algorithmic Sonnet Generation
Published in
arXiv.org(2018)External Links:
TL
TL;DR
This work provides an approach for generating beautiful poetry that includes several novel elements that improve over the state of the art, leading to metrical, rhyming poetry with many human-like qualities.
Abstract
We provide an approach for generating beautiful poetry. Our sonnet-generation algorithm includes several novel elements that improve over the state of the art, leading to metrical, rhyming poetry with many human-like qualities. These novel elements include in-line punctuation, part of speech restrictions, and more appropriate training corpora. Our work is the winner of the 2018 PoetiX Literary Turing Test Award for computer-generated poetry.
References34 items
1
Image Inspired Poetry Generation in XiaoIce
2
Deep-speare: A joint neural model of poetic language, meter and rhyme
3
Chinese Poetry Generation with a Working Memory Model
4
The machine poetry generator imitating Du Fu's styles
5