paper-with-me

홈 › Papers

Erato: Automatizing Poetry Evaluation

2023-10-31 · Manex Agirrezabal, Hugo Gonçalo Oliveira, Aitor Ormazabal

We present Erato, a framework designed to facilitate the automated evaluation of poetry, including that generated by poetry generation systems. Our framework employs a diverse set of features, and we offer a brief overview of Erato's capabilities and its potential for expansion. Using Erato, we compare and contrast human-authored poetry with automatically-generated poetry, demonstrating its effectiveness in identifying key differences. Our implementation code and software are freely available under the GNU GPLv3 license.

📄 PDF Abstract BibTeX arXiv:2310.20326

Code (1)

manexagirrezabal/erato 공식 구현

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

A Survey on Intelligent Poetry Generation: Languages, Features, Techniques, Reutilisation and Evaluation

2017-09-01 · WS 2017 9 · Hugo Gon{\c{c}}alo Oliveira

Poetry generation is becoming popular among researchers of Natural Language Generation, Computational Creativity and, broadly, Artificial Intelligence. To produce text that may be regarded as poetry, poetry generation sy…

Text Generation

BACON: Deep-Learning Powered AI for Poetry Generation with Author Linguistic Style Transfer

2021-12-14 · Alejandro Rodriguez Pascual

This paper describes BACON, a basic prototype of an automatic poetry generator with author linguistic style transfer. It combines concepts and techniques from finite state machinery, probabilistic models, artificial neur…

Style Transfer

Automatic Poetry Generation with Mutual Reinforcement Learning

2018-10-01 · EMNLP 2018 10 · Xiaoyuan Yi, Maosong Sun, Ruoyu Li, Wenhao Li

Poetry is one of the most beautiful forms of human language art. As a crucial step towards computer creativity, automatic poetry generation has drawn researchers{'} attention for decades. In recent years, some neural mod…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Sentimental Poetry Generation

2020-12-01 · ICON 2020 12 · Kasper Aalberg Røstvold, Björn Gambäck

The paper investigates how well poetry can be generated to contain a specific sentiment, and whether readers of the poetry experience the intended sentiment. The poetry generator consists of a bi-directional Long Short-T…

Learning Rhyming Constraints using Structured Adversaries

2019-09-15 · IJCNLP 2019 11 · Harsh Jhamtani, Sanket Vaibhav Mehta, Jaime Carbonell, Taylor Berg-Kirkpatrick

Existing recurrent neural language models often fail to capture higher-level structure present in text: for example, rhyming patterns present in poetry. Much prior work on poetry generation uses manually defined constrai…