Generate and Revise: Reinforcement Learning in Neural Poetry
- URL: http://arxiv.org/abs/2102.04114v1
- Date: Mon, 8 Feb 2021 10:35:33 GMT
- Title: Generate and Revise: Reinforcement Learning in Neural Poetry
- Authors: Andrea Zugarini, Luca Pasqualini, Stefano Melacci, Marco Maggini
- Abstract summary: We propose a framework to generate poems that are repeatedly revisited and corrected, as humans do, in order to improve their overall quality.
Our model generates poems from scratch and it learns to progressively adjust the generated text in order to match a target criterion.
We evaluate this approach in the case of matching a rhyming scheme, without having any information on which words are responsible of creating rhymes and on how to coherently alter the poem words.
- Score: 17.128639251861784
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Writers, poets, singers usually do not create their compositions in just one
breath. Text is revisited, adjusted, modified, rephrased, even multiple times,
in order to better convey meanings, emotions and feelings that the author wants
to express. Amongst the noble written arts, Poetry is probably the one that
needs to be elaborated the most, since the composition has to formally respect
predefined meter and rhyming schemes. In this paper, we propose a framework to
generate poems that are repeatedly revisited and corrected, as humans do, in
order to improve their overall quality. We frame the problem of revising poems
in the context of Reinforcement Learning and, in particular, using Proximal
Policy Optimization. Our model generates poems from scratch and it learns to
progressively adjust the generated text in order to match a target criterion.
We evaluate this approach in the case of matching a rhyming scheme, without
having any information on which words are responsible of creating rhymes and on
how to coherently alter the poem words. The proposed framework is general and,
with an appropriate reward shaping, it can be applied to other text generation
problems.
Related papers
- REFFLY: Melody-Constrained Lyrics Editing Model [50.03960548399128]
We introduce REFFLY, the first revision framework designed to edit arbitrary forms of plain text draft into high-quality, full-fledged song lyrics.
Our approach ensures that the generated lyrics retain the original meaning of the draft, align with the melody, and adhere to the desired song structures.
arXiv Detail & Related papers (2024-08-30T23:22:34Z) - Unsupervised Melody-to-Lyric Generation [91.29447272400826]
We propose a method for generating high-quality lyrics without training on any aligned melody-lyric data.
We leverage the segmentation and rhythm alignment between melody and lyrics to compile the given melody into decoding constraints.
Our model can generate high-quality lyrics that are more on-topic, singable, intelligible, and coherent than strong baselines.
arXiv Detail & Related papers (2023-05-30T17:20:25Z) - Unsupervised Melody-Guided Lyrics Generation [84.22469652275714]
We propose to generate pleasantly listenable lyrics without training on melody-lyric aligned data.
We leverage the crucial alignments between melody and lyrics and compile the given melody into constraints to guide the generation process.
arXiv Detail & Related papers (2023-05-12T20:57:20Z) - PoeticTTS -- Controllable Poetry Reading for Literary Studies [21.29478270833139]
We resynthesise poems by cloning prosodic values from a human reference recitation, and afterwards make use of fine-grained prosody control to manipulate the synthetic speech.
We find that finetuning our TTS model on poetry captures poetic intonation patterns to a large extent which is beneficial for prosody cloning and manipulation.
arXiv Detail & Related papers (2022-07-11T13:15:27Z) - PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised
Poetry Generation [42.12348554537587]
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.
We propose an unsupervised approach to generate poems following any given meter and rhyme scheme.
arXiv Detail & Related papers (2022-05-24T17:09:55Z) - Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics
Features [37.45490765899826]
We present a novel framework to generate sonnets that does not require training on poems.
Specifically, a content planning module is trained on non-poetic texts to obtain discourse-level coherence.
We also design a constrained decoding algorithm to impose the meter-and-rhyme constraint of the generated sonnets.
arXiv Detail & Related papers (2022-05-03T23:44:28Z) - CCPM: A Chinese Classical Poetry Matching Dataset [50.90794811956129]
We propose a novel task to assess a model's semantic understanding of poetry by poem matching.
This task requires the model to select one line of Chinese classical poetry among four candidates according to the modern Chinese translation of a line of poetry.
To construct this dataset, we first obtain a set of parallel data of Chinese classical poetry and modern Chinese translation.
arXiv Detail & Related papers (2021-06-03T16:49:03Z) - Acrostic Poem Generation [26.604889384391726]
We propose a new task in the area of computational creativity: acrostic poem generation in English.
Acrostic poems are poems that contain a hidden message; typically, the first letter of each line spells out a word or short phrase.
Our experiments show that the acrostic poems generated by our baseline are received well by humans and do not lose much quality due to the additional constraints.
arXiv Detail & Related papers (2020-10-05T18:00:15Z) - MixPoet: Diverse Poetry Generation via Learning Controllable Mixed
Latent Space [79.70053419040902]
We propose MixPoet, a novel model that absorbs multiple factors to create various styles and promote diversity.
Based on a semi-supervised variational autoencoder, our model disentangles the latent space into some subspaces, with each conditioned on one influence factor by adversarial training.
Experiment results on Chinese poetry demonstrate that MixPoet improves both diversity and quality against three state-of-the-art models.
arXiv Detail & Related papers (2020-03-13T03:31:29Z) - Introducing Aspects of Creativity in Automatic Poetry Generation [2.792030485253753]
Poetry Generation involves teaching systems to automatically generate text that resembles poetic work.
A deep learning system can learn to generate poetry on its own by training on a corpus of poems and modeling the particular style of language.
We propose taking an approach that fine-tunes GPT-2, a pre-trained language model, to our downstream task of poetry generation.
arXiv Detail & Related papers (2020-02-06T20:44:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.