SARCH: Multimodal Search for Archaeological Archives

TL;DR

This paper presents SARCH, a multimodal search system for archaeological archives that integrates text, images, and tables from scanned PDFs to improve retrieval effectiveness.

Contribution

It introduces a novel multi-modal search pipeline tailored for archaeological documents, combining multiple retrieval strategies for enhanced accuracy.

Findings

Hybrid retrieval approach outperforms single-modality methods

Effective extraction and classification of images from scanned PDFs

Preliminary results show promising retrieval performance

Abstract

In this paper, we describe a multi-modal search system designed to search old archaeological books and reports. This corpus is digitally available as scanned PDFs, but varies widely in the quality of scans. Our pipeline, designed for multi-modal archaeological documents, extracts and indexes text, images (classified into maps, photos, layouts, and others), and tables. We evaluated different retrieval strategies, including keyword-based search, embedding-based models, and a hybrid approach that selects optimal results from both modalities. We report and analyze our preliminary results and discuss future work in this exciting vertical.