A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing

Kartik Goyal, Chris Dyer, Christopher Warren, Maxwell G’Sell, Taylor Berg-Kirkpatrick


Abstract
We propose a deep and interpretable probabilistic generative model to analyze glyph shapes in printed Early Modern documents. We focus on clustering extracted glyph images into underlying templates in the presence of multiple confounding sources of variance. Our approach introduces a neural editor model that first generates well-understood printing phenomena like spatial perturbations from template parameters via interpertable latent variables, and then modifies the result by generating a non-interpretable latent vector responsible for inking variations, jitter, noise from the archiving process, and other unforeseen phenomena associated with Early Modern printing. Critically, by introducing an inference network whose input is restricted to the visual residual between the observation and the interpretably-modified template, we are able to control and isolate what the vector-valued latent variable captures. We show that our approach outperforms rigid interpretable clustering baselines (c.f. Ocular) and overly-flexible deep generative models (VAE) alike on the task of completely unsupervised discovery of typefaces in mixed-fonts documents.
Anthology ID:
2020.acl-main.266
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2954–2960
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.266
DOI:
10.18653/v1/2020.acl-main.266
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.266.pdf
Video:
 http://slideslive.com/38929423