arXiv Open Access 2021

Generative Pre-Trained Transformer for Design Concept Generation: An Exploration

Qihao Zhu Jianxi Luo

Lihat Sumber

Abstrak

Novel concepts are essential for design innovation and can be generated with the aid of data stimuli and computers. However, current generative design algorithms focus on diagrammatic or spatial concepts that are either too abstract to understand or too detailed for early phase design exploration. This paper explores the uses of generative pre-trained transformers (GPT) for natural language design concept generation. Our experiments involve the use of GPT-2 and GPT-3 for different creative reasonings in design tasks. Both show reasonably good performance for verbal design concept generation.

Topik & Kata Kunci

cs.CL cs.LG

Penulis (2)

Qihao Zhu

Jianxi Luo

Format Sitasi

APA MLA BibTeX

Zhu, Q., Luo, J. (2021). Generative Pre-Trained Transformer for Design Concept Generation: An Exploration. https://arxiv.org/abs/2111.08489

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2021
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓