Design representation as semantic networks

Han, Jiarui; Luo, Jianxi

doi:10.1016/j.compind.2022.103791

Cited by 12 publications

(7 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…WordNet and ConceptNet have been the most used knowledge bases for this purpose (Linsey, Markman & Wood 2012;Georgiev & Georgiev 2018;Kan & Gero 2018;Goucher-Lambert & Cagan 2019;Han et al 2022). TechNet is a relatively newer knowledge base, trained on engineering design data, such as patent texts, and is more suitable than 4/18 ConceptNet, WordNet and other common-sense knowledge bases for assessing semantic distance or similarity between technological concepts (Sarica et al 2020(Sarica et al , 2023.…”

Section: Natural Language Processingmentioning

confidence: 99%

The innovation paradox: concept space expansion with diminishing originality and the promise of creative artificial intelligence

Sarica,

Luo

2024

Des. Sci.

View full text Add to dashboard Cite

Innovation, typically spurred by reusing, recombining and synthesizing existing concepts, is expected to result in an exponential growth of the concept space over time. However, our statistical analysis of TechNet, which is a comprehensive technology semantic network encompassing over 4 million concepts derived from patent texts, reveals a linear rather than exponential expansion of the overall technological concept space. Moreover, there is a notable decline in the originality of newly created concepts. These trends can be attributed to the constraints of human cognitive abilities to innovate beyond an ever-growing space of prior art, among other factors. Integrating creative artificial intelligence into the innovation process holds the potential to overcome these limitations and alter the observed trends in the future.

show abstract

Section: Natural Language Processingmentioning

confidence: 99%

The innovation paradox: concept space expansion with diminishing originality and the promise of creative artificial intelligence

Sarica,

Luo

2024

Des. Sci.

View full text Add to dashboard Cite

show abstract

“…Utilizing semantic relations to encapsulate design knowledge offers multiple benefits, facilitating enhanced reasoning, analysis, and manipulation of the knowledge embedded within design documents. This approach significantly improves the retrieval of design information, as demonstrated by Han et al (2022) and Sarica et al (2023), by making the data more accessible and interpretable. Furthermore, it substantially enhances the effectiveness of all NLP applications within the design domain (Giordano et al, 2024).…”

Section: Motivationmentioning

confidence: 99%

Towards the extraction of semantic relations in design with natural language processing

Giordano,

Consoloni,

Chiarello

et al. 2024

Proc. Des. Soc.

View full text Add to dashboard Cite

Natural Language Processing (NLP) has been extensively applied in design, particularly for analyzing technical documents like patents and scientific papers to identify entities such as functions, technical feature, and problems. However, there has been less focus on understanding semantic relations within literature, and a comprehensive definition of what constitutes a relation is still lacking. In this paper, we define relation in the context of design and the fundamental concepts linked to it. Subsequently, we introduce a framework for employing NLP to extract relations relevant to design.

show abstract

“…This is in line with other similar studies. For example, Sarica et al [50] interviewed twenty-five participants to understand their choices of the best computational representation of a specific design, and Zhu [51] interviewed ten engineers regarding their views towards a set of computationally generated design concepts.…”

Section: 𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 = 𝑇𝑃 𝑇𝑃 + 𝐹𝑃mentioning

confidence: 99%

A Comparison Study of Human and Machine-Generated Creativity

Sun

Han

2023

Journal of Computing and Information Science in Engineering

Self Cite

View full text Add to dashboard Cite

Creativity is a fundamental feature of human intelligence. However, achieving creativity is often considered a challenging task, particularly in design. In recent years, using computational machines to support people in creative activities in design, such as idea generation and evaluation, has become a popular research topic. Although there exist many creativity support tools, few of them could produce creative solutions in a direct manner, but produce stimuli instead. DALL·E is currently the most advanced computational model that could generate creative ideas in pictorial formats based on textual descriptions. This study conducts a Turing test, a computational test and an expert test to evaluate DALL·E's capability in achieving combinational creativity comparing with human designers. The results reveal that DALL·E could achieve combinational creativity at a similar level to novice designers and indicate the differences between computer and human creativity.

show abstract

Design representation as semantic networks

Cited by 12 publications

References 64 publications

The innovation paradox: concept space expansion with diminishing originality and the promise of creative artificial intelligence

The innovation paradox: concept space expansion with diminishing originality and the promise of creative artificial intelligence

Towards the extraction of semantic relations in design with natural language processing

A Comparison Study of Human and Machine-Generated Creativity

Contact Info

Product

Resources

About