Reliable Editions from Unreliable Components: Estimating Ebooks from Print Editions Using Profile Hidden Markov Models

TL;DR

This paper introduces a novel method using profile hidden Markov models to automatically generate accurate, print artifact-free ebooks from multiple print editions, benefiting accessibility and digital preservation.

Contribution

It applies profile HMMs to model and merge multiple print editions into high-quality ebooks, a novel approach in digital text processing.

Findings

Successfully produced ebooks with accurate transcription

Eliminated print artifacts like hyphenation and headers

Demonstrated on seven copies of a nineteenth-century novel

Abstract

A profile hidden Markov model, a popular model in biological sequence analysis, can be used to model related sequences of characters transcribed from books, magazines, and other printed materials. This paper documents one application of a profile HMM: automatically producing an ebook edition from distinct print editions. The resulting ebook has virtually all the desired properties found in a publisher-prepared ebook, including accurate transcription and an absence of print artifacts such as end-of-line hyphenation and running headers. The technique, which has particular benefits for readers and libraries that require books in an accessible format, is demonstrated using seven copies of a nineteenth-century novel.