Post-doctoral Research Associate in Computational Linguistics

About us:

King’s College London is home to the world’s largest Department of Digital Humanities, located within the Faculty of Arts & Humanities. We are internationally recognised for our interdisciplinary research and teaching at the intersection of the humanities and computational methods. The successful candidate will join the Computational Humanities research group, a vibrant and collaborative team dedicated to advancing data-driven approaches to historical, linguistic, and cultural research. This post is part of the 5-year project Computational Corpus Annotation for Quantitative Analysis of Latin Lexical Semantics (COALA), successfully evaluated by the ERC as a Consolidator Grant and funded by UKRI, led by Dr Barbara McGillivray.

About the role:

We are seeking a Postdoctoral Research Associate in Computational Linguistics to co-lead the computational stream of the COALA project.

This role is an exciting opportunity to contribute to a pioneering project at the intersection of natural language processing, historical linguistics, and computational humanities.

The postholder will co-lead the computational stream of the project, which involves developing novel algorithms for time-sensitive word sense disambiguation (WSD) in Latin, contributing to the creation of a 100-million-token annotated corpus, and conducting large-scale quantitative analyses of semantic change. You will work closely with Latin linguists to integrate linguistic insights into computational models and help build open-source tools and resources that will support future research in historical semantics and NLP.

You will be responsible to the Principal Investigator and will collaborate with a team of postdoctoral researchers and external advisors across linguistics, NLP, and classical studies.

This is a full-time post (35 hours per week) based in London at the KCL Strand Campus, and you will be offered a fixed-term contract until 31st January 2030.

About you:

To be successful in this role, we are looking for candidates to have the following skills & experience:

Essential criteria

• PhD awarded in Computational Linguistics, Natural Language Processing, or a closely related field or PhD near completion in Computational Linguistics, Natural Language Processing, or a closely related field*
• Demonstrated experience with computational semantics models, word sense disambiguation, or semantic change detection
• Proficiency in Python and relevant NLP libraries
• Experience working with large-scale corpora or annotation pipelines
• Strong publication record comparable with your career stage
• Ability to work collaboratively in interdisciplinary teams
• Excellent written and verbal communication skills

Desirable criteria

• Experience with historical texts or historical languages, especially Latin
• Familiarity with corpus annotation standards & tools
• Knowledge of diachronic NLP or time-sensitive semantic modelling
• Interest in digital humanities or historical linguistics