PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation

@article{Ormazabal2022PoeLMAM,
  title={PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation},
  author={Aitor Ormazabal and Mikel Artetxe and Manex Agirrezabal and Aitor Soroa Etxabe and Eneko Agirre},
  journal={ArXiv},
  year={2022},
  volume={abs/2205.12206}
}
Formal verse poetry imposes strict constraints on the meter and rhyme scheme of poems. Most prior work on generating this type of poetry uses existing poems for supervision, which are difficult to obtain for most languages and poetic forms. In this work, we propose an unsupervised approach to generate poems following any given meter and rhyme scheme, without requiring any poetic text for training. Our method works by splitting a regular, non-poetic corpus into phrases, prepending control codes… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 31 REFERENCES

Deep-speare: A joint neural model of poetic language, meter and rhyme

A joint architecture that captures language, rhyme and meter for sonnet modelling is proposed, which shows the importance expert evaluation for poetry generation, and that future research should look beyond rhyme/meter and focus on poetic language.

Full-FACE Poetry Generation

It is argued that this is the first poetry system which generates examples, forms concepts, invents aesthetics and frames its work, and so can be assessed favourably with respect to the FACE model for comparing creative systems.

Rhyming Knowledge-Aware Deep Neural Network for Chinese Poetry Generation

The experimental results demonstrate that the proposed rhyming knowledge-aware deep neural network for Chinese poetry generation is able to guide the style of those poems towards higher phonological compliance, fluency, coherence, and meaningfulness, as evaluated by human experts.

Automatically Generating Rhythmic Verse with Neural Networks

Two novel methodologies for the automatic generation of rhythmic poetry in a variety of forms are proposed that demonstrate that participants consider machine-generated poems to be written by humans 54% of the time and that participants rated a machine- generated poem to be the best amongst all evaluated.

Automatic Poetry Generation from Prosaic Text

This paper presents a framework for language models based on neural networks that is applied to the generation of poems in both English and French, and is equally evaluated for both languages.

A Multi-Modal Chinese Poetry Generation Model

A three-stage multi-modal Chinese poetry generation approach which can effectively capture character, phrase, and sentence information between contexts and improve the symmetry delivered in poems is proposed.

Multilingual extension and evaluation of a poetry generator*

The effort of adapting the same architecture to generate poetry in three different languages – Portuguese, Spanish and English is described.

PoeTryMe : a versatile platform for poetry generation

A prototype was implemented based on PoeTryMe to generate Portuguese poetry, using natural language processing resources for this language, and patterns that denote semantic relations in human-created poetry.

Chinese Poetry Generation with Planning based Neural Network

A novel two-stage poetry generating method which first plans the sub-topics of the poem according to the user’s writing intent, and then generates each line of the poems sequentially, using a modified recurrent neural network encoder-decoder framework.

Automatic Poetry Generation with Mutual Reinforcement Learning

A novel mutual reinforcement learning schema is proposed which simultaneously train two learners (generators) which learn not only from the teacher (rewarder) but also from each other to further improve performance.