Recent advances in recurrent neural networks
Recurrent neural networks (RNNs) are capable of learning features and long term
dependencies from sequential and time-series data. The RNNs have a stack of non-linear …
dependencies from sequential and time-series data. The RNNs have a stack of non-linear …
A survey on intelligent poetry generation: Languages, features, techniques, reutilisation and evaluation
HG Oliveira - Proceedings of the 10th international conference on …, 2017 - aclanthology.org
Poetry generation is becoming popular among researchers of Natural Language
Generation, Computational Creativity and, broadly, Artificial Intelligence. To produce text that …
Generation, Computational Creativity and, broadly, Artificial Intelligence. To produce text that …
On the creativity of large language models
G Franceschelli, M Musolesi - arXiv preprint arXiv:2304.00008, 2023 - arxiv.org
Large Language Models (LLMs) are revolutionizing several areas of Artificial Intelligence.
One of the most remarkable applications is creative writing, eg, poetry or storytelling: the …
One of the most remarkable applications is creative writing, eg, poetry or storytelling: the …
Natural language generation using deep learning to support MOOC learners
Among all the learning resources within MOOCs such as video lectures and homework, the
discussion forum stood out as a valuable platform for students' learning through knowledge …
discussion forum stood out as a valuable platform for students' learning through knowledge …
The AI ghostwriter effect: When users do not perceive ownership of AI-generated text but self-declare as authors
Human-AI interaction in text production increases complexity in authorship. In two empirical
studies (n1= 30 & n2= 96), we investigate authorship and ownership in human-AI …
studies (n1= 30 & n2= 96), we investigate authorship and ownership in human-AI …
Comparative analysis of vision transformers and convolutional neural networks in osteoporosis detection from X-ray images
Within the scope of this investigation, we carried out experiments to investigate the potential
of the Vision Transformer (ViT) in the field of medical image analysis. The diagnosis of …
of the Vision Transformer (ViT) in the field of medical image analysis. The diagnosis of …
Copyright in generative deep learning
G Franceschelli, M Musolesi - Data & Policy, 2022 - cambridge.org
Machine-generated artworks are now part of the contemporary art scene: they are attracting
significant investments and they are presented in exhibitions together with those created by …
significant investments and they are presented in exhibitions together with those created by …
Creativity and machine learning: A survey
G Franceschelli, M Musolesi - ACM Computing Surveys, 2024 - dl.acm.org
There is a growing interest in the area of machine learning and creativity. This survey
presents an overview of the history and the state of the art of computational creativity …
presents an overview of the history and the state of the art of computational creativity …
DeepRapper: Neural rap generation with rhyme and rhythm modeling
Rap generation, which aims to produce lyrics and corresponding singing beats, needs to
model both rhymes and rhythms. Previous works for rap generation focused on rhyming …
model both rhymes and rhythms. Previous works for rap generation focused on rhyming …
Natural language statistical features of LSTM-generated texts
M Lippi, MA Montemurro… - … on Neural Networks …, 2019 - ieeexplore.ieee.org
Long short-term memory (LSTM) networks have recently shown remarkable performance in
several tasks that are dealing with natural language generation, such as image captioning …
several tasks that are dealing with natural language generation, such as image captioning …