Answers are grounded in this paper and cite their sources.
The rapid growth in the number of digital texts has posed challenges for information professionals to make them more navigable and usable. These challenges have prompted researchers to develop different approaches to creating semantic descriptions for these resources aiming at more efficient and effective navigation and granular access to specific textual content. In this poster, we report on ongoing work that utilizes cluster‐oriented machine learning algorithms to recover the logical relationships embedded in the typographical layout of book indexes, structures that are lost when standard page‐level OCR scanning techniques are deployed on the index pages of digitized historical books. Recovering typographical logic would aid in the construction of semantic representation of indexes that can provide granular access to digital texts thus improving textual navigation.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2021) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: