CultureBot improves cultural heritage search with graph guided chat
CultureBot: A Framework for Retrieval-Augmented Exploration of Cultural Heritage Data
Computation and Language
Summary
Searching cultural heritage collections can be hard because the items have many complex links like places, times, and images, but most searches only use simple keywords. The authors built CultureBot, a system that talks with you in natural language and uses a knowledge graph to find better answers tied directly to the original data. They tested it on a large cultural collection and found experts preferred its answers, especially for detailed reasoning and diverse responses. This shows that combining structured knowledge graphs with conversational search can help people explore cultural collections more deeply while keeping trust in the sources.
What this means in practice
- •For digital museum curators: Offer visitors interactive natural language search that reveals relationships across cultural heritage collections with accurate source links.
- •For cultural heritage platform developers: Integrate graph guided retrieval and generation to improve depth and relevance of user queries in cultural data portals.
Authors
Vasileios Karampinis, Angelos Vlachos, Giorgos Filandrianos, Maria Lymperaiou, Paraskevi Tzouveli, Chrysoula Zerva, Giorgos Stamou
Abstract
Digital cultural heritage collections encode rich relations among objects, places, periods, providers, images, and source institutions, yet users typically access them through keyword search and faceted browsing. We present CULTUREBOT, an interactive framework for natural-language exploration of cultural heritage collections that combines knowledge-graph-guided retrieval, lexical-semantic retrieval, and source-linked generation. CULTUREBOT maps user queries to structured catalogue relations, enriches retrieved records with textual evidence, and generates answers that link back to the underlying repository records. We instantiate the framework on 81,852 SearchCulture records and release an online demonstration. In an expert evaluation involving six cultural-heritage specialists, 55 persona-grounded queries, and 250 evaluations, the graph-guided system was rated significantly higher than two general-purpose assistants and a non-graph ablation, with the largest gains in evidence grounding, diversity, reasoning, and completeness. These results support graph-guided retrieval as a practical way to expose the relational structure of cultural collections through conversational access while preserving links to catalogue evidence.