The quantitative turn: NLP and AI Methods in Romance Linguistics
In recent decades, linguistic research has embraced new methods that prioritize data-driven approaches and mathematical modeling. This shift, known as the “Quantitative Turn” (Kortmann 2021), stems from a desire to move beyond theories based solely on the intuitions of a few experts. Instead, researchers now harness readily available data from sources like social media and online platforms, such as Amazon Mechanical Turk (Winter 2022). These sources provide access to more spontaneous language use, offering a richer view of how people communicate.
However, working with this type of data comes with challenges. Social media posts, speech transcripts, and other unstructured language data often need to be organized or “cleaned” before they can be analyzed. Doing this manually is both time-consuming and expensive. Fortunately, advancements in Natural Language Processing (NLP) and Artificial Intelligence (AI) offer solutions.
Technologies like word2vec (Mikolov et al. 2013), BERT (Devlin et al. 2019), and others based on transformer architectures (Vaswani et al. 2017) are capable of processing vast amounts of data. These tools allow researchers to analyze patterns in language without extensive manual effort. Applications range from studying how dialects change over time to developing tools for understanding text, such as parsers for unstructured data and systems for resolving pronouns in sentences (Dobrovolskii 2021).
Despite these advances, many of the latest NLP and AI techniques have focused on widely spoken languages like English. As a result, Romance languages and their diverse dialects remain underrepresented in this research (Kellert & Zaman 2023). This gap stands for a missed opportunity to apply cutting-edge tools to answer important questions about Romance languages and to explore their unique linguistic characteristics.
This workshop invites researchers to explore how NLP and AI methods can address challenges in Romance Linguistics, with a focus on adapting these tools to less-studied Romance languages and varieties.



Suggested topics
We welcome contributions that address questions such as:
How can we handle unstructured data in linguistic research?
How can Romance languages benefit from the latest NLP and AI tools?
What steps can ensure reliable linguistic insights from large-scale social media data?
How can collaborations between linguists and AI experts advance the study of Romance languages?
What role does the Quantitative Turn play in language policy for Romance-speaking communities?
What unique challenges do Romance languages pose for NLP and AI development?

Submission Guidelines:
• Working languages: English, German, and Romance Languages
• Abstract Length: 4000 characters (including white spaces and bibliography)
• Submission Deadline: January 20, 2025
• Event Dates: September 22nd-25th, 2025
• Location: Konstanz, Germany
Please submit your abstract as a PDF attachment to iris.ferrazzo@uni-bonn.de. Include your name, affiliation, and contact information in the body of the email. We welcome submissions from researchers from diverse disciplinary backgrounds. The decision on the choice of abstracts will be announced on January 31st, 2025.
Event Coordinators:
• Iris Ferrazzo (Universität Bonn / Bonner Center for Digital Humanities)
• Olga Kellert (Universität A Coruña / Universität Göttingen)
For any inquiries or further information, please contact iris.ferrazzo@uni-bonn.de.