Cangjie's Poetry

Weidi Zhang (CN), Donghao Ren (CN)

Humans and machines are in constant conversation. Intelligent machines today are not only observers of the world, they also make creative decisions. If AI imitates human beings to generate a symbolic system and actively communicate with us based on their own understandings of the universe, to what degree will their messages and meanings recontextualize our coexistence? Cangjie’s Poetry is an intelligent multimodal system designed as a conceptual response and prototype to the future language. This work is inspired by an ancient Chinese legendary historian, Cangjie (c.2650 BCE), who invented one of the oldest logographic systems (Chinese characters) based on the appearance of everything on the earth. Our AI system named Cangjie was developed by training a neural network to learn the constructions and principles of over 9000 Chinese characters. After successfully learning, the system can constantly observe surrounding environments via a camera and transform the live-streaming feed into a cluster of new symbols constructed by Chinese strokes, just as the historian Cangjie did thousands of years ago. Meanwhile, we implement a computer vision system to simultaneously generate localized descriptive sentences of images in natural language to create meanings for this symbolic system. 

Cangjie's Poetry transforms the machine's interpretation of surroundings into an interactive semantic experience. It constructs conceptual and futuristic communication between humans and machines. This work is not only a conceptual response to the tension and fragility in the coexistence of humans and machines but also a conceptual expression of a future language that reflects on ancient truths, a way to evoke enchantment in this era of artificial intelligence. Like the legendary historian Cangjie nearly 5000 years ago, the Cangjie system continuously writes poetry with humans collaboratively as long as the real world exists.

Humans and machines are in constant conversation. Intelligent machines today are not only observers of the world, they also make creative decisions. If AI imitates human beings to generate a symbolic system and actively communicate with us based on their own understandings of the universe, to what degree will their messages and meanings recontextualize our coexistence? Cangjie’s Poetry is an intelligent multimodal system designed as a conceptual response and prototype to the future language. This work is inspired by an ancient Chinese legendary historian, Cangjie (c.2650 BCE), who invented one of the oldest logographic systems (Chinese characters) based on the appearance of everything on the earth. Our AI system named Cangjie was developed by training a neural network to learn the constructions and principles of over 9000 Chinese characters. After successfully learning, the system can constantly observe surrounding environments via a camera and transform the live-streaming feed into a cluster of new symbols constructed by Chinese strokes, just as the historian Cangjie did thousands of years ago. Meanwhile, we implement a computer vision system to simultaneously generate localized descriptive sentences of images in natural language to create meanings for this symbolic system. 

Cangjie's Poetry transforms the machine's interpretation of surroundings into an interactive semantic experience. It constructs conceptual and futuristic communication between humans and machines. This work is not only a conceptual response to the tension and fragility in the coexistence of humans and machines but also a conceptual expression of a future language that reflects on ancient truths, a way to evoke enchantment in this era of artificial intelligence. Like the legendary historian Cangjie nearly 5000 years ago, the Cangjie system continuously writes poetry with humans collaboratively as long as the real world exists.

www.zhangweidi.com/cangjiepoetry
cangjiepoetry.com
vimeo.com/687583045

 

Artist, interactive visualization, intelligent system and sound design: Weidi Zhang 

Intelligent system design and implementation: Donghao Ren 

 

Special thanks to: Prof. George Legrady, Prof. Marko Peljhan, Prof. Curtis Roads, Experimental Visualization Lab, UC Santa Barbara Media Arts and Technology Program at University of California, Santa Barbara 

 

With support from: SYMADES 2021 Research Grant, University of California, Santa Barbara

Weidi Zhang (CN) is new media artist and researcher. Her works investigate a speculative assemblage in the context of experimental data visualization, Interactive Intelligence system design, and immersive media. Currently, she is working on a PhD degree in the Media Arts and Technology Program at the University of California, Santa Barbara. Donghao Ren (CN) is a research scientist in data visualization and machine learning. He was born in Beijing, China. He received his PhD degree in Computer Science from the University of California, Santa Barbara. He worked on interactive visualization authoring systems, visualization frameworks, and visual analytic tools for machine learning.

Weidi Zhang (CN) is new media artist and researcher. Her works investigate a speculative assemblage in the context of experimental data visualization, Interactive Intelligence system design, and immersive media. Currently, she is working on a PhD degree in the Media Arts and Technology Program at the University of California, Santa Barbara. Donghao Ren (CN) is a research scientist in data visualization and machine learning. He was born in Beijing, China. He received his PhD degree in Computer Science from the University of California, Santa Barbara. He worked on interactive visualization authoring systems, visualization frameworks, and visual analytic tools for machine learning.