Name: eLex 2025
Start: 2025-11-17T14:00:00+01:00
End: 2025-11-20T18:00:00+01:00
Location: Bled, Slovenia

eLex 2025

from Monday, November 17, 2025 (2:00 PM) to Thursday, November 20, 2025 (6:00 PM)

Monday, November 17, 2025
2:00 PM CLASSLA-Express 2.0: Corpora vs. LLMs
CLASSLA-Express 2.0: Corpora vs. LLMs
2:00 PM - 4:00 PM
Contributions

2:00 PM Opening

2:15 PM Large language models and generative artificial intelligence: introduction - Slobodan Beliga

2:40 PM Some examples of using AI tools in Slovenian lexicography - Polona Gantar

3:05 PM Applying ChatGPT to Croatian phraseology and related lexicographic tasks - Ivana Filipović Petrović (Croatian Academy of Sciences and Arts)
4:00 PM CLASSLA-express 2.0: Hands-on exercises
CLASSLA-express 2.0: Hands-on exercises
4:00 PM - 7:00 PM
Contributions

4:00 PM Corpora and AI-driven interfaces: Extracting linguistic data

5:00 PM Corpora and AI-driven interfaces: Creating definitions and providing usage examples of phraseological units for dictionaries

6:00 PM Corpora and AI-driven interfaces: Distinguishing literal and figurative uses of phraseological units
Tuesday, November 18, 2025

8:00 AM

8:00 AM - 9:00 AM

9:00 AM

9:00 AM - 9:30 AM
9:30 AM Keynote 1
Keynote 1
9:30 AM - 10:30 AM
Contributions

9:30 AM Large language models for lexicography - Marko Robnik-Šikonja
10:30 AM Coffee break
Coffee break
10:30 AM - 11:00 AM
11:00 AM
11:00 AM - 1:00 PM
Contributions

11:00 AM Retention of English words from interaction with dictionaries and GenAI Chatbots - Robert Lew Bartosz Ptasznik

11:30 AM Automating Adjectival Microstructures in Monolingual Dictionaries: A New Method Combining Embeddings and LLMs - Enikő Héja László Simon Veronika Lipp

12:00 PM Automatic Non-recorded Sense Detection for Swedish through Word Sense Induction with fine-tuned Word-in-Context models - Dominik Schlechtweg Emma Sköldberg Shafqat Mumtaz Virk James White Simon Hengchen

12:30 PM Automatic Detection of Word Sense Shift from Corpus Data - Ondřej Herman
11:00 AM - 1:00 PM
Contributions

11:00 AM Compiling bilingual dictionaries: AI-Assisted translation of Italian Multiword Expressions into English and French - Annalisa Greco Matteo Delsanto Andrea Di Fabio Lorenzo Mori Cristina Onesti Daniele Paolo Radicioni Calogero Jerik Scozzaro

11:30 AM Neology in Practice: Lexicographic and Terminological Approaches to Lexical Innovation - Jelena Kallas Kristina Koppel Kris Heylen Ilan Kernerman Ana Ostroški Anić Federica Vezzani Špela Arhar Holdt

12:30 PM Enhancing Lexicographic Access for Deaf and Hard-of-Hearing Learners: A Digital Greek Sign Language Dictionary with AI-Powered Language Support - Isidora Despotidou Zoe Gavriilidou
11:00 AM - 1:00 PM
Contributions

11:00 AM Parsing of Explanatory dictionary - Iryna Ostapova Yevhen Kupriianov Mykyta Yablochkov

11:30 AM Vision-Enabled Language Models in Lexicographical Digitisation: A Case Study of Anton Thor Helle's 1732 Dictionary - Madis Jürviste Tiina Paet

12:00 PM GramatiKat: A Corpus-Based Tool for Detecting Morphological Anomalies and Paradigm Variation - Dominika Kovarikova

12:30 PM Modeling and structuring of a bilingual French-Chinese phraseological dictionary: neural automatic approach for ontology and lexicography - Lian Chen
1:00 PM Lunch
Lunch
1:00 PM - 2:30 PM
2:30 PM
2:30 PM - 4:00 PM
Contributions

2:30 PM The Dictionary of Contemporary Serbian Language (RSSJ): Advanced Automation and Other Challenges - Ranka Stanković Rada Stijović Mihailo Škorić Cvetana Krstev

3:00 PM Lexical-Semantic Resources as a Culture-Aware Basis for Benchmarking and Evaluation of LLMs - Nathalie Norman Sanni Nimb Sussi Olsen Nina Schneidermann Bolette S. Pedersen

3:30 PM Do dictionary users prefer definitions by lexicographers or by LLM-s? - Maria Tuulik Ene Vainik Margit Langemets Eleri Aedmaa Lydia Risberg Esta Prangel Kristina Koppel Sirli Zupping
2:30 PM - 4:00 PM
Contributions

2:30 PM Documenting the Final Days of Monolingual English Learners’ Dictionaries Using the Archived Web - Geraint Paul Rees

3:00 PM Mapping Slovene Learner Vocabulary to CEFR Scales with AI-assisted Methods - Mojca Stritar Kučuk

3:30 PM AI- and Corpus-Based Strategies for Identifying Phraseme Constructions: A Pilot Study on Croatian Repetitive Constructions - Slobodan Beliga Ivana Filipović Petrović
2:30 PM - 4:00 PM
Contributions

2:30 PM Exploring the constructicographic potential of lexicographic data and language models: The case of the Estonian Nominal Quantifier Construction - Heete Sahkai Geda Paulsen Ene Vainik Jelena Kallas Ahto Kiil Katrin Tsepelina Kertu Saul Arvi Tavast

3:00 PM The Mangalam Dictionary of Buddhist Sanskrit: automating lexicographic data with generative LLMs - Ligeia Lugli

3:30 PM Why a dedicated dictionary device is more appropriate than an app for primary school learners - Lorna Morris
4:00 PM Coffee break
Coffee break
4:00 PM - 4:30 PM

4:30 PM A - part 1
A - part 1
4:30 PM - 5:00 PM

B - part 1
B - part 1
4:30 PM - 5:00 PM

C - part 1
C - part 1
4:30 PM - 5:00 PM

5:00 PM A - part 2
A - part 2
5:00 PM - 5:30 PM

B - part 2
B - part 2
5:00 PM - 5:30 PM

C - part 2
C - part 2
5:00 PM - 5:30 PM

5:30 PM A - part 3
A - part 3
5:30 PM - 6:00 PM

B - part 3
B - part 3
5:30 PM - 6:00 PM

C - part 3
C - part 3
5:30 PM - 6:00 PM

7:00 PM Reception (sponsored by Cambridge University Press)
Reception (sponsored by Cambridge University Press)
7:00 PM - 8:00 PM
Wednesday, November 19, 2025
9:00 AM Keynote 2
Keynote 2
9:00 AM - 10:00 AM
Contributions

9:00 AM LLMs and Lexicography at the Dutch Language Institute - Carole Tiberius Jesse de Does
10:05 AM
10:05 AM - 10:30 AM
Contributions

10:05 AM The lemma dilemma, Slovene version - Polona Gantar Cyprian Laskowski Simon Krek
10:05 AM - 10:30 AM
Contributions

10:05 AM Lexicography and Generative Artificial Intelligence for contextualised meaning - Theo J.D. Bothma Rufus H. Gouws
10:05 AM - 10:30 AM
Contributions

10:05 AM An Electronic Ukrainian Dictionary as a Derussification Tool - Vasyl Starko Andriy Rysin
10:30 AM Coffee break
Coffee break
10:30 AM - 11:00 AM
11:00 AM
11:00 AM - 12:00 PM
Contributions

11:00 AM Making Sense of the Past: AI-Assisted Historical Word Sense Disambiguation and the OED - Elinor Hawkes Phoebe Nicholson Will Rogers

11:30 AM Bridging human and AI perspectives: semantic annotation of generic nouns in German - Iván Arias-Arias Elena Martín-Cancela
11:00 AM - 12:00 PM
Contributions

11:00 AM Exploring the power of generative artificial intelligence for automatic term extraction from small samples - Lena De Pourcq Marie Grégoire Leonardo Zilio

11:30 AM Lexicom at 25: reflections on the changing world of lexicography and language technology - Michael Rundell Miloš Jakubíček Vojtěch Kovář Ondřej Matuška Michal Cukr
11:00 AM - 12:00 PM
Contributions

11:00 AM Navigating linguistic diversity: modelling diatopic and bibliographic information with TEI Lex-0 - Veronika Engler Karlheinz Mörth Stephan Procházka Michaela Rausch-Supola Daniel Schopper

11:30 AM Artificial intelligence in English dictionary entries compiled in Slovar krajšav - Mojca Kompara Lukančič
12:00 PM
12:00 PM - 1:00 PM
Contributions

12:00 PM lexicographR: R infrastructure to develop and deploy digital dictionaries from scratch - Ligeia Lugli

12:00 PM Digitalization of Romanian dictionaries - Mititelu Catalin

12:00 PM Accelerating the lexicographic process with automatic methods and AI - Nathalie Norman Nicolai Hartvig Sørensen Jonas Jensen Kirsten Appel Sanni Nimb

12:00 PM Presenting verbal aspect data in a learner’s dictionary: Devices and usage scenarios - Sarah Piepkorn

12:00 PM The Challenges of Syntactic Descriptions of Multiword Expressions in Electronic Lexicography - Verginica Barbu Mititelu Voula Giouli Gražina Korvel Chaya Liebeskind Irina Lobzhanidze Rusudan Makhachashvili Stella Markantonatou Alexandra Markovic Ivelina Stoyanova

12:00 PM The dictionary of pluricentric Portuguese project: theoretical aspects - Tanara Zingano Kuhn

12:00 PM A Bazaar Among Cathedrals – Leveraging Wikidata as an Open Marketplace for Lexicographic Data - Gregor Middell

12:00 PM Implementing Frames in the Phrase-based Active Dictionary: why Frames are needed but FrameNet can only be a partial solution - Laura Rebosio

12:00 PM Project of a Specialized Dictionary Website - Mykyta Yablochkov Alona Dorozhynska Iryna Ostapova Iuliia Verbynenko

12:00 PM The Hare and the Tortoise: Pipeline for Latvian Information and Communication Technologies Secondary Term Formation - Dace Šostaka Inguna Skadiņa

12:00 PM Exploring Derivational Families through Intelligent Lexicography - Krešimir Šojat Kristina Kocijan

12:00 PM Comparative Analysis of Medical Adjectives in Croatian General Dictionaries - Martina Pavić Daša Farkaš

12:00 PM CJVT Igre: New Word Games Based on the Digital Dictionary Database of Slovene - Špela Arhar Holdt Iztok Kosem

12:00 PM Handling abstract constructions in a dictionary-based constructicon - Bálint Sass Éva Dömötör Balázs Indig Mátyás Lagos Cortes Veronika Lipp Márton Makrai Gergely Pethő

12:00 PM Qualitative Evaluation of LLM Translation of MWEs for Developing a Croatian Sense Repository - Ana Ostroški Anić Jaka Čibej Ivana Filipović Petrović Martina Pavić Siniša Runjaić Robert Sviben

12:00 PM Up to No Good: Exploiting Word Embeddings for an Automatic Extraction of Candidates for a Lexicon of Slovene Taboo Language - Jaka Čibej

12:00 PM Introducing DigiMet: a Psycholinguistic Database for Croatian Multi-Word Expressions - Jasmina Jelčić Čolakovac
1:00 PM Lunch
Lunch
1:00 PM - 2:30 PM
2:30 PM
2:30 PM - 4:00 PM
Contributions

2:30 PM Choosing Suitable Text Corpora for Identifying Collocations – A Case Study of a Large Reference Dictionary of Contemporary German - Luise Köhler Gregor Middell Alexander Geyken

3:00 PM The role of subjectivity in lexicography: Experiments towards data-driven labeling of informality - Lydia Risberg Eleri Aedmaa Maria Tuulik Margit Langemets Ene Vainik Esta Prangel Kristina Koppel Hanna Pook

3:30 PM So Close but Still Far: Case Study on Application of LLMs in Idioms Identification, Definition, and Generation of Illustrative Examples - Aleksandra Marković Ranka Stanković
2:30 PM - 4:00 PM
Contributions

2:30 PM Using Large Language Models to Generate Distractors for Language Games - Iztok Kosem Špela Arhar Holdt

3:00 PM Automated Transcription of Mixed-Script Dialectal Materials - Markus Kunzmann

3:30 PM Learner’s reactions to false polysemy - Tomasz Michta Ana Frankenberg-Garcia
2:30 PM - 4:00 PM
Contributions

2:30 PM Information seeking behavior of the English learner in the AI era - Anna Dziemianko Mojca M. Hočevar

3:00 PM Matching meaning: Evaluating ChatGPT’s ability to assign corpus examples to dictionary senses of polysemous sound-related verbs - Sylwia Wojciechowska

3:30 PM The DICI-A: A Learner Dictionary of Italian Collocations - Stefania Spina Fabio Zanda Irene Fioravanti Luciana Forti Damiano Perri Osvaldo Gervasi
4:00 PM Coffee break
Coffee break
4:00 PM - 4:30 PM
4:30 PM
4:30 PM - 6:00 PM
Contributions

4:30 PM How Effective is AI as a Language Consultant? - Urška Vranjek Ošlak

5:00 PM Corpus-Based Vocabulary Profiling for Ukrainian: From Lexical Analysis to the PULS Digital Learning Platform - Olena Synchak Vasyl Starko Mariana Burak Mykhaylo Svystun

5:30 PM Identifying the Most Representative Phraseological Units Using Language Corpora and Artificial Intelligence for Lexicography: The Case of Slovenian Comparative Phrasemes - Matej Meterc Nataša Jakop
4:30 PM - 6:00 PM
Contributions

4:30 PM Corpus-Based Methods and AI-Assisted Terminography for Contextonym Analysis - Antonio San Martín

5:00 PM User interaction with assistive technology for a thorough evaluation of a WCAG 2-compliant e-dictionary: assessing the accessibility of the Diccionario de la Lengua Española, v. 23.8 - Jesús Torres del Rey María García Garmendia

5:30 PM From Word of the Year to Word of the Week: Daily-updated Monitor Corpora for 25 Languages - Ondřej Herman Miloš Jakubíček Jan Kraus Vít Suchomel
4:30 PM - 6:00 PM
Contributions

4:30 PM Compiling a candidate list of taboo constructions for an under-resourced language - Monique Rabé Martin J. Puttkammer Gerhard B. van Huyssteen

5:00 PM You get it through lexicography: extracting suppressed language from LLMs using lexicographic scenarios as jailbreaking tools - Esra Abdelzaher Ágoston Tóth

5:30 PM A Corpus-Based Dictionary for the Endangered Megrelian Language - Irina Lobzhanidze Rusudan Gersamia
7:00 PM Gala dinner
Gala dinner
7:00 PM - 10:00 PM
Thursday, November 20, 2025
9:00 AM Keynote 3
Keynote 3
9:00 AM - 10:00 AM
Contributions

9:00 AM We need to talk about data structures in lexicography - Michal Měchura
10:05 AM
10:05 AM - 10:30 AM
Contributions

10:05 AM Contrasting a new AI-powered dictionary designed for on-screen reading with electronic dictionaries that have evolved from print editions - Ana Frankenberg-Garcia
10:05 AM - 10:30 AM
Contributions

10:05 AM LLM-Assisted Dialect Lexicography: Challenges and Opportunities in Processing Historical Bavarian Dialects - Philipp Stöckle Daniel Elsner Wolfgang Koppensteiner Katharina Korecky-Kröll
10:05 AM - 10:30 AM
Contributions

10:05 AM Toward a corpus-based multilingual terminology database for Intercultural Communication - María Iglesias Vázquez Charlotte Venema Marie Steffens
10:30 AM Coffee break
Coffee break
10:30 AM - 11:00 AM
11:00 AM
11:00 AM - 12:30 PM
Contributions

11:00 AM DMLEX on Wikibase: Legacy dictionaries as collaboratively editable dataset - Simon Krek Primož Ponikvar Andraž Repar Iztok Kosem David Lindemann

11:30 AM Image-to-Sense Alignment Using AI Tools - Andrej Perdih Dejan Gabrovšek Janoš Ježovnik

12:00 PM Woordpeiler: A New Tool for Visualizing and Analyzing Lexical Trends in Contemporary Dutch - Kris Heylen Vincent Prins Katrien Depuydt Jesse de Does Laura van Eerten Thomas Haga
11:00 AM - 12:30 PM
Contributions

11:00 AM Inductive Categorization for Conceptual Analysis with LLMs: A Case Study from the Humanitarian Encyclopedia - Loryn Isaacs Santiago Chambó Pilar León-Araúz

11:30 AM Passive Vocabulary of Czech Native Speakers: A Statistical Approach - Marek Blahuš Miloš Jakubíček Vojtěch Kovář František Kovařík

12:00 PM Automatically Updated Corpora of EU National Parliaments with Terminology Extraction in Twenty Languages - Marek Blahuš Ota Mikušek
11:00 AM - 12:30 PM
Contributions

11:00 AM A Pipeline for Automated Dictionary Creation with Optional Human Intervention - Thomas Widmann

11:30 AM Better something than nothing: Analysis of GPT-4 performance in identifying Croatian proverbs - Nikola Bakarić
12:30 PM

12:30 PM - 12:45 PM
2:00 PM Globalex workshop on Lexicography and Neology
Globalex workshop on Lexicography and Neology
2:00 PM - 6:00 PM
Contributions

2:00 PM Welcome

2:10 PM From Poetry to Lexicon: The Role of Lexicography in Documenting Literary Neologisms - Nikos Mathioudakis

2:35 PM A Study into the Translation of Chinese Culture-bound Neologisms in Large Chinese-English Dictionaries - Jinhong Huang

3:00 PM Lexicographical treatment of homophonic neologisms in Chinese dictionaries - Jiang Li Wang Yi

3:25 PM The energy crisis in Germany and its impact on general language vocabulary - Alexander Geyken

4:20 PM ENEOLI Wikibase: A collaborative working platform for the European Network on Lexical Innovation - Ana Salgado David Lindemann

4:45 PM Evaluating Suitability of Open-Weight Large Language Models for Neologism Detection in Lithuanian: Methodological and Practical Issues - Marius Glebus

5:10 PM The challenge of AI-generated neologisms - Cécile Poix Natalya Shevchenko

5:35 PM Discussion and closing

Choose timezone