Generating Reflective Questions for Engaging Gallery Visitors in ArtMuse

Sujatha Das Gollapalli, Mingzhe Du, See-Kiong Ng

AAAI 2023 pp. 16434-16436

doi:10.1609/AAAI.V37I13.27070 /aaai/2023/gollapalli2023aaai-generating/

Abstract

Human guides in museums and galleries are professionally trained to stimulate informal learning in visitors by asking low-risk, open-ended reflective questions that enable them to focus on specific features of artifacts, relate to prior experiences, and elicit curiosity as well as further thought. We present ArtMuse, our AI-powered chatbot for asking reflective questions in context of paintings. Our reflective question generation model in ArtMuse was trained by applying a novel combination of existing models for extractive question answering and open-domain chitchat. User evaluation studies indicate that we are able to generate fluent and specific reflective questions for paintings that are highly-engaging.

PDF AAAI Semantic Scholar

Cite

Text

Das Gollapalli et al. "Generating Reflective Questions for Engaging Gallery Visitors in ArtMuse." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27070

Markdown

[Das Gollapalli et al. "Generating Reflective Questions for Engaging Gallery Visitors in ArtMuse." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/gollapalli2023aaai-generating/) doi:10.1609/AAAI.V37I13.27070

BibTeX

@inproceedings{gollapalli2023aaai-generating,
  title     = {{Generating Reflective Questions for Engaging Gallery Visitors in ArtMuse}},
  author    = {Das Gollapalli, Sujatha and Du, Mingzhe and Ng, See-Kiong},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16434-16436},
  doi       = {10.1609/AAAI.V37I13.27070},
  url       = {https://mlanthology.org/aaai/2023/gollapalli2023aaai-generating/}
}