Exploring a gallery with intelligent labels

Ordinary labels on museum or gallery objects compromise the competing demands of differing visitors, curators and educators. Although adaptive hypermedia systems offer a degree of personalization to the visitor, they do not go as far as they might. Intelligent labeling can achieve higher levels of personalization, and this is desirable because it leads to a more coherent and educational visit, and because the overall interaction with the hypermedia resource becomes more like an active conversation, and less like reading a static book. We use natural language generation techniques, from the field of artificial intelligence, to generate personalized labels on demand. Our system can deliver these labels as Web pages, in an electronic gallery, or as synthesized speech in a physical gallery. We discuss aspects of coherence and conversationality, and illustrate them with a simple case.