Andrei Popescu-Belis, Àlex Atrio, Valentin Minder, Aris Xanthos, Gabriel Luthier, Simon Mattei, Antonio Rodriguez
| Challenge: | Neural language models cannot learn constraints from data, which is scarce for a well-resourced language such as French. |
| Approach: | They propose a system that combines neural language models with constraints that can be set by users on form, topic, emotion, and rhyming scheme. |
| Outcome: | The proposed system generates poems and stanzas using LMs and rule-based algorithms . it has been demonstrated at public events and log analysis shows that users found it engaging . |
Similar Papers
Automatic Poetry Generation from Prosaic Text (2020.acl-main)
Copied to clipboard
| Challenge: | In recent years, successful approaches have emerged to accurately model various aspects of natural language. |
| Approach: | They propose to combine neural networks with a poetry generation system that only uses standard text as input . they use standard text to model syntactic well-formedness and topical coherence . |
| Outcome: | The proposed framework is applied to the generation of poems in English and French . it uses standard, non-poetic text and its output is constrained to confer a poetic character . |
PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating formal verse poetry use existing poems for supervision, which are difficult to obtain for most languages and poetic forms. |
| Approach: | They propose an unsupervised approach to generate formal verse poetry without supervision . they use control codes to describe meter and rhyme scheme constraints, and train a transformer language model . |
| Outcome: | The proposed method generates poems that follow any given meter and rhyme scheme without training . it is comparable to those written by humans and generates comparable quality poems . |
Acrostic Poem Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Acrostic poems contain a hidden message; typically, the first letter of each line spells out a word or short phrase. |
| Approach: | They propose a task for acrostic poem generation in English with multiple constraints . they define the task as a generation task with multiple constraint constraints based on a conditional neural language model and a neural rhyming model . |
| Outcome: | The proposed task is based on a baseline model and a neural rhyming model. |
Deep-speare: A joint neural model of poetic language, meter and rhyme (P18-1)
Copied to clipboard
| Challenge: | a recent surge of interest in deep learning has led to creative applications for poetry generation . a novel joint architecture captures language, rhyme and meter for sonnet modelling . |
| Approach: | They propose a joint architecture that captures language, rhyme and meter for sonnet modelling. |
| Outcome: | The proposed architecture captures language, rhyme and meter for sonnet modelling. |
There Once Was a Really Bad Poet, It Was Automated but You Didn’t Know It (2021.tacl-1)
Copied to clipboard
| Challenge: | Existing algorithms for limerick generation are difficult to use, as they must follow strict structural, meter, and rhyming constraints. |
| Approach: | They propose a system for automatic limerick generation that outperforms state-of-the-art models. |
| Outcome: | The proposed system outperforms state-of-the-art models and rule-based models in generating limericks. |
Syllable-level lyrics generation from melody exploiting character-level language model (2024.findings-eacl)
Copied to clipboard
| Challenge: | Pre-trained language models specifically designed at the syllable level are not available. |
| Approach: | They propose to exploit character-level language models for syllable-level lyrics generation from symbolic melody. |
| Outcome: | The proposed system improves coherence and correctness of generated lyrics without training expensive language models. |
Instruction-Guided Poetry Generation in Arabic and Its Dialects (2026.findings-acl)
Copied to clipboard
Abdelrahman Sadallah, Kareem Elozeiri, Mervat Abassy, Rania Elbadry, Mohamed Anwar, Abed Alhakim Freihat, Preslav Nakov, Fajri Koto
| Challenge: | Existing literature on Arabic poetry has focused on analysis tasks such as interpretation or metadata prediction, e.g., rhyme schemes and titles. |
| Approach: | They propose to use a large-scale instruction-based dataset to generate Arabic poetry based on predefined criteria such as style and rhyme . |
| Outcome: | The proposed model can generate poetry that is aligned with user requirements, based on automated metrics and human evaluation with native Arabic speakers. |
Evaluating Diversity in Automatic Poetry Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for creative text generation are not evaluated regarding how different generated poems are from existing training sets. |
| Approach: | They evaluate the diversity of automatically generated poetry by comparing distributions of generated poetry to distributions in human poetry along structural, lexical, semantic and stylistic dimensions. |
| Outcome: | The proposed model types show that style-conditioning and character-level modeling increases diversity across virtually all dimensions. |
Automatic Poetry Generation with Mutual Reinforcement Learning (D18-1)
Copied to clipboard
| Challenge: | Existing models for automatic poetry generation are based on maximum likelihood estimation (MLE) MLE-based models tend to remember common patterns of the poetry corpus, which results in loss-evaluation mismatch. |
| Approach: | They propose to model the criteria and use them as explicit rewards to guide gradient update by reinforcement learning to motivate the model to pursue higher scores. |
| Outcome: | The proposed model outperforms the current state-of-the-art model and improves on Chinese poetry. |
ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | End-to-end models learn to complete a task by directly learning all steps, without intermediary algorithms such as hand-crafted rules or post-processing. |
| Approach: | They propose to train end-to-end poetry generation conditioned on styles such as rhyme, meter, and alliteration . they pre-train ByGPT5, a new token-free decoder-only language model, and fine-tune it on a custom corpus of English and German quatrains . |
| Outcome: | The proposed model outperforms other models on a large custom corpus of English and German quatrains while being more parameter efficient and performing favorably compared to humans. |