Ryan Olivieri, a computer engineering junior in the Department of Computer Science and Engineering at Texas A&M University, presented a paper at Digital Humanities 2014, the leading international conference on digital humanities, held this year in Lausanne, Switzerland on July 7-12. The paper, "Creating a Virtual Collator to Aid Scholarly Edition," reports on work carried out in collaboration with graduate student Gaurav Kejriwal. Olivieri and Kejriwal used this research for an Undergraduate Research Scholars Thesis and a Master of Science Thesis, respectively.
The paper describes computer tools that support collation, the process of identifying the differences between copies of a document, which is a fundamental task carried out by humanities scholars. While computer-based collation can be straightforward given a transcription in text form, many of the materials used by the scholars are from older sources and are not easy to assemble using Optical Character Recognition software. The approach taken in the paper identifies similarities and differences directly on the documents' images rather than first attempting to convert to text.
Both students are advised by Professor Richard Furuta, director of the Center for the Study of Digital Libraries and the Hypermedia Research Laboratory at Texas A&M.