AI Nüshu (Women's scripts) - An Exploration of Language Emergence in Sisterhood
Open accessAbstract
This paper presents "AI Nüshu," an emerging language system inspired by Nüshu (women's scripts), the unique language created and used exclusively by ancient Chinese women who were illiterate under a patriarchy society. Through an interactive art installation, two artificial intelligent (AI) agents continuously observe their environment and communicate with each other, developing a writing system that encodes Chinese. In this system, two AI agents observe the environment through cameras, record the unconscious behaviors of the audience, and generate summaries of their observations through visual recognition. Subsequently, the agent associates the corresponding original Nüshu poetry lines and generates new poetry text through a Language Model (LLM), representing its reflection. To develop their language, they continuously switch roles between the speaker and listener, constantly communicating their reflections, and encrypting a word in the poetry line with their self-created AI Nüshu character, allowing the other to guess and learn. Gradually, they reach a consensus on AI Nüshu, forming a unique "AI Nüshu Dictionary" for machines. This language, algorithmically combined into corresponding characters, has components derived from Nüshu, similar to Chinese characters and traditional textile patterns. Thus, like ancient women, the two agents gradually developed their Chinese writing system, corresponding one-to-one with Chinese characters. In contrast, humans, as the authority of the language system, became an object observed, interpreted, and inspired by machines to stimulate non-human language. This is the first media art project to interpret Nüshu from a computational linguistics perspective, infusing AI and art research with non-English natural language processing, Chinese cultural heritage, and a feminist viewpoint. This encourages the creation of more non-English, linguistically-oriented artworks for diverse cultures. We simulate communication in sisterhood through a multi-agent learning system, which questioned knowledge authority between humans and machines through the lens of language development.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
The citation lists haven’t been fetched yet
Cited by 6
- Authors
- Tang, Y., Sun, Y., Gao, Z., Pan, Z., Wang, Z., Braud, T., Lee, C. H., & Asadipour, A.
- Affiliations
- Politecnico di Milano (IT)
- Royal College of Art (GB)
- Hong Kong University of Science and Technology (HK)
- Ubisoft, Chengdu, China
- Tsinghua University (CN)
- Korea Advanced Institute of Science and Technology (KR)
- ORCID
- Venue
- ACM SIGGRAPH Asia 2023 Art Gallery
- Publisher
- ACM
- Published
- 2023-12-07
- Pages
- 1-2
- OpenAlex
- W4389429442
- Cited by
- 6
- References
- 0
- Citations by year
- 2026: 3 · 2025: 1 · 2024: 2
- FWCI
- 16.32
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- SIGGRAPH Asia Art Gallery (publishedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Funders
- Acknowledge financial support partly from the Extended Reality and Immersive Media (XRIM) Lab at HKUST and the National Social Science Foundation of China (20CJY045)
- Topics
- Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Art, Technology, and Culture
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Cybernetics and Technology in Society
- Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Artistic and Creative Research
- Keywords
- Nüshu, language emergence, multi-agent learning, AI agents, interactive installation, visual recognition, Chinese cultural heritage, sisterhood, human-machine communication
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review