April 3, 2024
Day/Time/Room
May 15, 2024 | 10:15 a.m. to 11:15 a.m. | Ski-U-Mah Room
Title: Single Source Publishing
Presenter: Dione Mentis, COO and Senior Architect, Coko
Description: Traditional publishing workflows involve a fragmented process – content is created in isolation, converted to multiple file formats, then passed between teams handling editing, production, distribution and preservation. This convoluted workflow hampers efficiency and heightens overhead for publishers and librarians alike.
However, an emergent approach called single source publishing (SSP) offers respite by streamlining publishing using a unified file format across the entire process. Rather than a serialized hand-off of content between siloed teams working in different formats, SSP enables concurrent collaboration within one system using shared source files.
For librarians, the advantages of this consolidated workflow are multi-fold. SSP lowers resource demands by reducing hand-offs, production steps, version proliferation and duplications. Content can shift smoothly from creation to dissemination without format conversion bottlenecks.
Preservation also benefits since SSP utilizes fewer intermediate file representations, limiting risks of data loss or corruption. The unified format persisting across the workflow remains viable for the long-term.
By employing web standards like HTML, SSP further ensures continuity and guards against format obsolescence. Librarians can depend on HTML viability over decades. For distribution, SSP streamlines exports to various end-user formats from this single standards-based source.
With publishing labor reduced through workflow consolidation, librarians may redirect efforts from production logistics to higher-value tasks around service enhancement and community support. Staff workload rebalances from technical publishing minutiae to more impactful objectives.
In essence, SSP promises librarians savings in time, costs and headaches through a unified publishing chain – allowing fuller focus on reader experience. This emerging approach warrants consideration by libraries seeking relief from fragmentary workflows.
Title: Automating JATS XML Tagging With ChatGPT
Presenter: Matthew Vaughn (he/him/his), Open Publishing Librarian, Indiana University
Description: While significant progress has been made in streamlining JATS XML publication workflows, efficiently converting article submission files into JATS XML galleys remains challenging for smaller publishers. The Journal Article Tag Suite (JATS) is a global standard for scholarly journal publishing, indexing, sharing, and archiving. Motivated by the advantages of XML publishing, the Indiana University open access journal publishing program has explored a number of options to expand our use of JATS. In 2023, we began experimenting with the generative AI tool ChatGPT to assess its potential in automating the JATS conversion step in our publishing workflow. Our results demonstrated that ChatGPT can effectively tag plain-text research article content in accurate, publishable JATS.
In an effort to automate XML tagging for the journal Studies in Digital Heritage (SDH), we designed several prompts to direct ChatGPT in tagging each section of a research article in our specific JATS format. Guided by prompts that provided relevant XML examples, ChatGPT was able to produce JATS-compliant tagging from plain-text article content. At the section level, the JATS produced by ChatGPT was comparable in accuracy to our vendor-produced JATS. Eventually, this approach along with several additional steps was able to produce a publication-ready JATS galley which we then posted to SDH.
While our experiment with automating JATS XML tagging demonstrates that large language models like ChatGPT are capable of performing this type of work with high accuracy, the current token limitations of ChatGPT 3.5 necessitate a piecemeal approach which makes this method too unwieldy for large scale adoption at this point. Nevertheless, if the token limit were substantially increased, and if we could input all our prompts simultaneously, fully automated JATS tagging may be within reach.