About the Event
The NLP & Text Mining Seminar is a gathering of researchers and practitioners interested in the latest advancements in natural language processing and text mining. This edition focuses on the underlying dimensions of semantics change, exploring how the meaning of words evolves over time and what artificial intelligence can reveal about these shifts.
This seminar is organized by Leuven.AI and KU Leuven. The event takes place at the Faculty of Arts (room Het Salon, LETT 00.24) in Leuven and is available hybrid for remote attendees.
Speaker
Bách Phan-Tất
PhD Researcher — QLVL Research Group, KU Leuven · Marie Skłodowska-Curie Doctoral Network CASCADE
Bách is a PhD researcher at the QLVL (Quantitative Lexicology and Variational Linguistics) group at KU Leuven. His research centres on the underlying dimensions of conceptual change — using quantitative and computational methods to detect, interpret, and explain how concepts and word meanings shift over time.
Before KU Leuven he completed an MSc in Linguistics at the University of Stirling, where he won the Research Based Learning Prize for the best Master’s dissertation in Literature and Languages. His work sits at the cross-roads of linguistics, cognitive science, and NLP — with particular interest in semantic change, distributional semantics, interpretability, and concept modelling.
He has published and presented at leading venues including EACL, ACL, EMNLP, NeurIPS, and Evolang — both as sole and co-author. Beyond academic research he has worked on applied NLP problems: large language models, speech recognition, and text-to-speech systems.
Topics
Semantic Change ↗
Language is not static — the same word can mean something quite different a century from now. Semantic change is the study of how and why word meanings shift over time. Some words broaden (dog once meant a specific breed), others narrow (meat once meant any food), and some drift entirely (awful used to mean “inspiring awe”). In the age of large text corpora and AI, researchers can now track these shifts computationally — detecting not just that a word changed, but how: which collocates appeared, which argument structures shifted, which contexts disappeared.
Natural Language Processing (NLP) ↗
Natural Language Processing is the field of AI concerned with teaching computers to read, understand, and generate human language. It powers the spell-checker in your browser, the voice assistant on your phone, machine translation, and — more recently — large language models like GPT and Claude. For researchers studying language change, NLP provides the tools: word embeddings, contextual representations, and distributional models that can encode how a word is used across millions of documents and across time.
Text Mining ↗
Text mining is the art of extracting structured insight from unstructured text at scale. Think of it as data mining, but the raw material is language rather than numbers. It includes techniques like named entity recognition, sentiment analysis, topic modelling, and pattern extraction. Applied to historical corpora — digitised newspapers, scientific journals, parliamentary debates — text mining enables researchers to observe how language and concepts have evolved across decades and disciplines.
Event Details
Date: 31 March 2026
Time: 11:00 – 12:00 (Europe/Brussels)
Location: Faculty of Arts, Leuven — room Het Salon (LETT 00.24)
Format: Hybrid (in-person + online)
Organizers: Leuven.AI / KU Leuven
Event Type: Seminar
Target Audience: Researchers, practitioners, and enthusiasts in the fields of NLP, text mining, and computational linguistics.
Attend
Organised by
Leuven.AI
Leuven.AI is KU Leuven’s cross-faculty AI institute, bringing together over 300 researchers from engineering, sciences, humanities, and medicine. It coordinates AI research, education and events in and around Leuven — making it one of the most active academic AI hubs in Belgium.
↗ ai.kuleuven.beQLVL — KU Leuven
The Quantitative Lexicology and Variational Linguistics group is part of KU Leuven’s Faculty of Arts. QLVL specialises in corpus-based and computational approaches to language variation and change — combining traditional linguistics with modern data science methods. It is the research home of this seminar’s speaker.
↗ arts.kuleuven.be/ling/qlvl