Language, Literature, and the New Digital Humanities
Chair: Du, Keli

Discovering Works in Historic Languages in HathiTrust with Language Models: A Case Study in Armeno-Turkish

Sirin, Hale (1); Bolcakan, Ali (2); Li, Sabrina (1); Lippincott, Thomas (1)

1: Johns Hopkins University; 2: University of Michigan

HTML XML

This study presents an experimental workflow to train and implement language models to discover works in Armeno-Turkish—vernacular Turkish written in Armenian script— in HathiTrust, as a test case for a more generalizable solution to increase the discoverability of documents in historic languages.


Streamlining Text Encoding Initiative (TEI), International Image Interoperability Framework (IIIF), and Mirador: Theoretical and Practical Considerations for Interactive Critical Editions

Hanneken, Todd R.

St. Mary’s University (San Antonio), United States of America

HTML XML

TEI can encode the information necessary to derive a IIIF Presentation manifest and annotations for each line of a manuscript. A streamlined model increases accessibility to scholars. The paper will demonstrate the method used to create print, hypertext, and annotated image editions of a palimpsest recovered with multispectral imaging.


New Developments in Digital Scholarly Editions for Non-Latin Literature

Nagasaki, Kiyonori (1); Ohmukai, Ikki (2); Shimoda, Masahiro (3)

1: International Institute for Digital Humanities, Japan and Keio University; 2: The University of Tokyo; 3: Musashino University

HTML XML

This study aims to improve this situation by presenting useful methods for constructing scholarly editions with non-Latin script literature.


Racial and ethnic bias in machine translation and AI-generated texts

Rykowska, Aleksandra

Jagiellonian University in Kraków, Poland

HTML XML

Proposal presents a study of racial and ethnical bias in automatically generated stories and automatic translations in languages: English, German, French, Polish and Lithuanian. The study reveals how stereotypes shine through the obtained data on a semantic and linguistic level, and on the basis of sentiment analysis.


The MLA International Bibliography’s History of English-Language Literary Studies, 1982-2023

Algee-Hewitt, Mark (2); Fredner, Erik (1)

1: University of Virginia; 2: Stanford University

The authors negotiated the first release of more than 900,000 bibliographic records from The Modern Language Association International Bibliography. By analyzing the records’ metadata created by expert indexers, which describe scholarly essays, chapters, and books, we write a new quantitative history of the last forty years of English-language literary study.