Google Research @ Sydney Event
Honoured to have been selected to attend the Google Research @ Sydney Event at the first Google research facility in Australia with my colleague and lab mate.
About Me
Naomi Baes is a doctoral researcher at the intersection of Psychology and Natural Language Processing, supported by an Australian Government Research Training Program Scholarship and supervised by Professor Nick Haslam and Dr Ekaterina Vylomova. Her research examines conceptual change in mental health concepts using language models and historical corpora. She co-developed SIBling, a framework for evaluating semantic change across three dimensions (Sentiment, Intensity, and Breadth) and LSC-Eval (with Dr Haim Dubossarsky and Raphaël Merx), a benchmarking resource that leverages LLM-generated diachronic corpora to evaluate methods for detecting semantic change. Her work has been presented at leading venues including ACL, IC2S2, and EMNLP, where she applies these approaches to diverse corpora to trace meaning shifts and their social and cultural drivers. She also contributes to shared tasks (BRIGHTER) and serves on program committees (NLP4Democracy; SEM2025).
Interests
- Computational Linguistics
- Computational Social Science
- Natural Language Processing
- Psychology
- Semantic Change
Education
PhD, Psychology/ Natural Language Processing
University of Melbourne (2023-)
Graduate Diploma in Psychology (Advanced) with Honours
University of Melbourne
Research Program
My research investigates how concepts change their meaning, focusing on mental health. With my PhD supervisors, I have developed a novel linguistic framework (SIBling) and measures to model lexical semantic change (LSC) along three dimensions that are typically overlooked by existing approaches.
Key Contributions:
- SIBling: A theoretical model integrating insights from historical linguistics and psychology, reducing six types of LSC into three core dimensions: Sentiment, Intensity, and Breadth (SIB). [Prototype]
- SIB Toolkit: Our computational implementation of SIBling, quantifying semantic change across SIB, plus related features (salience and thematic content). Designed for broad application across the social sciences and language domains (scientific, media, everyday).
- LSC-Eval: An evaluation framework that uses LLM-generated synthetic corpora to simulate kinds of LSC and validate LSC detection methods, identifying optimal dimension- and domain-specific approaches. [Prototype]
- Applications: I apply SIBling to trace the historical semantic evolution of mental health-related concepts (e.g., autism, schizophrenia), analysing related cultural dynamics like concept creep, pathologisation, and stigmatisation.
This program: (1) offers a multidimensional model of conceptual change (SIBling), (2) develops or identifies computational tools for its application, (3) establishes a principled evaluation framework for LSC detection methods (LSC-Eval), and (4) demonstrates its value through detailed case studies. This body of work lays the groundwork for future extensions across disciplines (e.g., law, humanities) and languages.
Featured Publications
Relevant Publications
(2025).
LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data.
ACL Findings.
(2024).
A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applications.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics.
(2024).
What should we call mental ill health? Historical shifts in the popularity of generic terms.
PLOS Mental Health.
(2024).
The structure and evolution of social psychology: a co-citation network analysis.
The Journal of Social Psychology.
(2024).
A search for commonalities in defining the common good: Using folk theories to unlock shared conceptions.
The British Journal of Social Psychology.
Invited Talks
Recent News
Quick Updates
12 Sept 2025 @ 3:30 PM — Presenting “Dimensions of Semantic Change: Validation and Application of the SIBling Framework” at the University of Gothenburg (Humanisten). Part of the full-day conference Change is Key! – Using LLMs in the Humanities and Social Sciences (event link).
5 Aug – 30 Sept 2025 — Interning at Change is Key! (8 weeks). The program develops computational tools to trace how language, society, and culture evolve, applying NLP and corpus methods to study semantic change and variation across linguistics, digital humanities, and the social sciences.
28 July 2025 — Presented our ACL Findings paper LSC-Eval: A General Evaluation Framework for Assessing Methods for Measuring Lexical Semantic Change with LLM-Generated Synthetic Data, at ACL 2025 (Vienna, Austria) during Poster Session 5 (6:00–7:30 PM).
23 July 2025 — Presented a poster on two frameworks for modeling conceptual change — SIBling and LSC-Eval — at IC2S2’25 (Norrköping, Sweden), the International Conference on Computational Social Science.
New corpus data and scripts publicly available — see Resources tab.