Detecting Footnotes in 32 million pages of ECCO

Abstract

In "An Answer to the Question: What is Enlightenment?", the eighteenth-century German philosopher Immanuel Kant responded to a big question buried in a little footnote. But you wouldn't know it, because contemporary editions of Kant's famous essay no longer reproduce the parenthetical directive that Kant's original essay printed right under the essay's title in the December issue of the Berlinische Monatsschrift in 1784: "S. Decemb. 1783. S. 516." (See December 1783, p. 516). And, in fact, page 516 in the December volume of the Berlinische Monatsschrift 1783 has a footnote: "What is Enlightenment? This question is nearly as important as: what is truth? And should certainly be answered before one starts to enlighten! But I have yet to find it answered anywhere."

Digital Editions as Distant Supervision for Layout Analysis of Printed Books

“…To train and evaluate layout models, we must link digital editions to page images. This coarse-grained page-level alignment allows us to evaluate models' retrieval accuracy, supporting user queries for images [11] or footnotes [2]. Most models and evaluations of layout analysis, however, require a finer-grained assignment of rectangular or polygonal image zones to particular regions.…”