Raphaël Barman ; Maud Ehrmann ; Simon Clematide ; Sofia Ares Oliveira ; Frédéric Kaplan - Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers

jdmdh:6107 - Journal of Data Mining & Digital Humanities, January 19, 2021, HistoInformatics - https://doi.org/10.46298/jdmdh.6107
Combining Visual and Textual Features for Semantic Segmentation of Historical NewspapersArticle

Authors: Raphaël Barman ; Maud Ehrmann ; Simon Clematide ; Sofia Ares Oliveira ; Frédéric Kaplan

    The massive amounts of digitized historical documents acquired over the last decades naturally lend themselves to automatic processing and exploration. Research work seeking to automatically process facsimiles and extract information thereby are multiplying with, as a first essential step, document layout analysis. If the identification and categorization of segments of interest in document images have seen significant progress over the last years thanks to deep learning techniques, many challenges remain with, among others, the use of finer-grained segmentation typologies and the consideration of complex, heterogeneous documents such as historical newspapers. Besides, most approaches consider visual features only, ignoring textual signal. In this context, we introduce a multimodal approach for the semantic segmentation of historical newspapers that combines visual and textual features. Based on a series of experiments on diachronic Swiss and Luxembourgish newspapers, we investigate, among others, the predictive power of visual and textual features and their capacity to generalize across time and sources. Results show consistent improvement of multimodal models in comparison to a strong visual baseline, as well as better robustness to high material variance.


    Volume: HistoInformatics
    Section: HistoInformatics
    Published on: January 19, 2021
    Accepted on: July 3, 2020
    Submitted on: February 17, 2020
    Keywords: Computer Science - Computer Vision and Pattern Recognition,Computer Science - Computation and Language,Computer Science - Information Retrieval,Computer Science - Machine Learning
    Funding:
      Source : OpenAIRE Graph
    • Media Monitoring of the Past; Funder: Swiss National Science Foundation; Code: 173719

    13 Documents citing this article

    Consultation statistics

    This page has been seen 3257 times.
    This article's PDF has been downloaded 1120 times.