Page Embeddings: Extracting and Classifying Historical Documents with Generic Vector Representations

TY - CHAP

T1 - Page Embeddings: Extracting and Classifying Historical Documents with Generic Vector Representations

AU - Schnober, Carsten

AU - Smit, Renate

AU - Kuruppath, Manjusha

AU - Pepping, Kay

AU - van Wissen, Leon

AU - Petram, Lodewijk

PY - 2024/11/18

Y1 - 2024/11/18

N2 - We propose a neural network architecture designed to generate region and page embeddings for boundary detection and classification of documents within a large and heterogeneous historical archive. Our approach is versatile and can be applied to other tasks and datasets. This method enhances the accessibility of historical archives and promotes a more inclusive utilization of historical materials.

AB - We propose a neural network architecture designed to generate region and page embeddings for boundary detection and classification of documents within a large and heterogeneous historical archive. Our approach is versatile and can be applied to other tasks and datasets. This method enhances the accessibility of historical archives and promotes a more inclusive utilization of historical materials.

KW - Natural Language Processing

KW - Sequence Tagging

KW - Document Metadata Enhancement

KW - Machine Learning

M3 - Contribution to conference proceedings

VL - 3834

T3 - CEUR Workshop Proceedings

SP - 999

EP - 1011

BT - Proceedings of the Computational Humanities Research Conference 2024

ER -