Latest Past Events
The wandering verse: the computational detection of micro-intertexts in medieval literature
Intertextuality is a ubiquitous concept in literary studies, which – because of its notoriously open-ended nature – covers a variety of correspondences between texts. Signaling intertexts is an important editorial responsibility, because it can deepen one's reading experience of a literary work. Text reuse detection has become a popular task in the computational humanities too, although its evaluation is complicated by the lack of exhaustively annotated datasets of intertexts. Historic scholarship on medieval epics provides us with a wealthy inventory of micro-intertexts between medieval works, although their status is still hotly debated. Some philological communities have been keen on identifying intertexts as authorial features, whereas others have stressed their conventional status, especially in the wake of the oral-formulaic theory. In this talk, I will present a study on Middle Dutch epic literature, as well as an extension of this work to contemporary Middle English literature, in particular the bookshop theory surrounding the famous Auchinleck manuscript. I will argue that the intricate web woven by computationally detected intertexts can invite radically innovative readings of medieval literature.
Intensive 5-day entry level hands-on course on making digital editions of analogue and born-digital texts. In this course, participants will acquire a set of basic computer skills such as XML and handwritten text recognition to design a TEI-compatible Digital Scholarly Edition and deploy keystroke logging technology to record and analyse born-digital texts.
Historical Language Models and their Application to Word Sense Disambiguation
Large Language Models (LLMs) have become the cornerstone of current methods in Computational Linguistics. As the Humanities look towards computational methods in order to analyse large quantities of text, the question arises as to how these models are best developed and applied to the specificities of their domains. In this talk, I will address the application of LLMs to Historical Languages, following up on the MacBERTh project. In the context of the development of LLMs for Historical Languages, I will address how they can be specifically fine-tuned with efficiency to tackle the problem of Word Sense Disambiguation. In a series of experiments relying on data from the Oxford English Dictionary, I will highlight how non-parametric and metric learning approaches can be an interesting alternative to traditional fine-tuning methods that rely on classifiers that learn to disambiguate specific lemmas.