Intuitive Semantic Graph Tool for Enhanced Archive Exploration

Abstract

The paper introduces a new method for visualizing and navigating information in a cultural heritage archive in a simple and intuitive way. The proposed approach employs pre-trained language models to cluster data and create semantic graphs. The creation of multilayer maps enables deep exploration of archives with large datasets, while the ability to handle multilingual datasets makes it suitable for archives with documents in various languages. These features combine to provide a user-friendly tool that can be adapted to different contexts and provides an overview of archive contents, to allow even non expert users to successfully query the archive.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 1 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.