EURALEX 2026

Session

Computational & AI-Based Lexicography

29 Sept 2026, 16:30

OeAW Main Seat

Conveners

Computational & AI-Based Lexicography

• Jelena Kallas (Institute of the Estonian Langauge)

Computational & AI-Based Lexicography

• Iztok Kosem (University of Ljubljana & Jožef Stefan Institute)

Computational & AI-Based Lexicography

• Kristina Š. Despot (Institute for the Croatian Language)

Computational & AI-Based Lexicography

• Ana Ostroški Anić (Institute for the Croatian Language)

Computational & AI-Based Lexicography

• Gilles-Maurice de Schryver (Ghent University)

Computational & AI-Based Lexicography

• Kris Heylen (Dutch Language Institute (INT))

Computational & AI-Based Lexicography

• Miloš Jakubíček (Lexical Computing)

12. What LLMs Learn and What They Miss: Frequency Effects in the Automated Description of Korean Verbal Inflection

Li Cui (Yonsei University), Seol Namkung (Yonsei University), Jun Lee (Yonsei University), Hae-Yun Jung (Kyungpook National University), Kilim Nam (Yonsei University)

29/09/2026, 16:30

The present study aims to empirically examine the possibilities and limitations of LLMs as a lexicographic tool for Korean, by automatically generating inflected forms of Korean verb and adjective headwords using Large Language Models and contrasting the results with corpus frequency data. Focusing on the description of inflected forms of Korean verbs and adjectives, the study analyses in...

13. Chatbot Lexicography: Are GenAI LLMs Simply ‘Dictionaries’ In Their Own Right and ‘Lexicographers’ Plain and Simple?

Gilles-Maurice de Schryver (Ghent University)

29/09/2026, 17:00

At the time of the Euralex 2026 conference it will be nearly four years since the start of the GenAI revolution. The question that needs to be asked, and which will be answered, is thus: Is any of the past work in (academic) lexicography still of any relevance, or are LLM chatbots simply ‘dictionaries’ in their own right and ‘lexicographers’ plain and simple? The answer is a shocking one.

14. Lexicographic Resources for Inference-Based Semantic Text Processing System

Igor Boguslavsky (IA.A.Kharkevich Institute for Information Transmission Problems), Vyacheslav Dikonov (A.A.Kharkevich Institute for Information Transmission Problems), Evgeniya Inshakova (A.A.Kharkevich Institute for Information Transmission Problems), Alexandre Lazursky (A.A.Kharkevich Institute for Information Transmission Problems), Svetlana Timoshenko (A. A. Kharkevich Institute for Information Transmission Problems), Tatiana Frolova (A.A.Kharkevich Institute for Information Transmission Problems)

29/09/2026, 17:30

This paper describes the lexicographic resources developed for the ETAP text analysis and generation system, with particular emphasis on its semantic module, SemETAP. In our approach, semantic analysis is viewed not merely as the construction of a semantic representation, but as the derivation of inferences licensed by linguistic and background knowledge. The semantic component operates in two...

76. From Content to Code and Back: Evaluating Agentic Coding in LLMs for Building R Shiny Dictionary Interfaces

Iván Arias-Arias (Universidade de Santiago de Compostela), María José Domínguez Vázquez (Universidade de Santiago de Compostela), María Teresa Sanmarco Bande (Universidade de Santiago de Compostela), Carlos Valcárcel Riveiro (Universidade de Vigo)

01/10/2026, 14:00

While recent scholarship highlights the generative capabilities of LLMs for drafting lexicographic entries, their “black box” nature poses challenges regarding training corpora, linguistic representativity, and semantic hallu-cination. We propose that this opacity is less problematic when LLMs are deployed not as linguistic experts, but as software engineers. By leveraging LLMs as agentic...

77. Linking Dictionaries Through Meaning: A Sense-Level Evaluation of Taxonomy-Guided LLM Classification in Lexicography

Hanna Fischer (Research Center Deutscher Sprachatlas), Alfred Lameli (Research Center Deutscher Sprachatlas), Nathalie Mederake (Research Center Deutscher Sprachatlas), Nico Urbach (Research Center Deutscher Sprachatlas)

01/10/2026, 14:30

Despite the growing availability of digital dictionaries, semantic interoperability often remains limited to headwords, metadata, or article structures. Dictionary senses remain difficult to compare because they are shaped by different editorial traditions, segmentation practices, and levels of semantic granularity. This paper asks whether taxonomy-guided LLM classification can generate...

78. Historical Lexicography in the Age of AI: A Progress Report from the OED

Phoebe Nicholson (Oxford University Press), Will Rogers (Oxford University Press), Kate Wild (Oxford University Press)

01/10/2026, 15:00

The Oxford English Dictionary (OED) has long been recognized for its rigorous scholarship, yet it is equally notable for its readiness to adopt new technologies. As the volume and availability of linguistic evidence has grown in the digital era, so too have the challenges of efficiently revising a dictionary of this size and scope: in response, the OED has been undertaking a systematic...

79. Can Lexicographic Entries Embed Didactic Modules? A Case Study on LLM-Generated Outputs for a Dictionary Interface

Carlos Valcárcel Riveiro (Universidade de Vigo), María Teresa Sanmarco Bande (Universidade de Santiago de Compostela), Iván Arias-Arias (Universidade de Santiago de Compostela), María José Domínguez Vázquez (Universidade de Santiago de Compostela)

01/10/2026, 16:00

Digital dictionaries can become more than consultation tools when their internal data are sufficiently structured to be reused and transformed into embedded learning components. This paper evaluates whether large language models (LLMs) can convert PORTLEX entries, represented as reviewed JSON files, into interactive HTML didactic modules integrable into their corresponding dictionary entries....

80. Detecting Semantic Variation between German Standard Varieties through Word Embedding Comparison

Andrea Abel (Free University of Bolzano/Bozen & Eurac Research), Luca Ducceschi (Eurac Research), Federico Villa (Independent Researcher)

01/10/2026, 16:30

From a pluricentric perspective, German possesses several standard varieties, including the one used in South Tyrol (Italy). While automated lexicography has long focussed on differences of lexical forms across these varieties, meaning differences in formally identical words are more difficult to identify systematically. This study addresses such diatopic semantic variation by comparing usage...

81. The Ninth Art in Lexicography: The Power of Comic Strips

Gilles-Maurice de Schryver (Ghent University)

01/10/2026, 17:00

This paper presents the background to a book on the visual history of academic lexicography, being a sequence of hundreds of one-page comic strips, created through conversations with LLM chatbots and GenAI image generators, each page representing a major publication in the field. Of course, I knew that this submission would be a gamble: Would a comic version of a conference paper be taken...

99. Chatbots in Pedagogical Lexicography: Evaluating AI-Generated Dictionary Entries from Three LLMs

Elina Chadjipapa (Democritus University of Thrace), Zoe Gavriilidou (Democritus University of Thrace), Maria Mitsiaki (Democritus University of Thrace), Ifigeneia Dosi (Democritus University of Thrace)

02/10/2026, 09:00

As early as the eighteenth century, dictionary compilation has been perceived as a labor intensive and time-consuming endeavor, often characterized as meticulous and repetitive work (Lew, 2023). The creation of lexicographic articles, in particular, constitutes a complex process requiring the careful coordination of multiple parameters, including the target user group, users’ native language,...

101. The Reversal of a Bilingual Dictionary Using AI

Thordis Ulfarsdottir (The Árni Magnússon Institute for Icelandic Studies), Ellert Thor Johannsson (The Árni Magnússon Institute for Icelandic Studies)

02/10/2026, 09:20

This paper presents a pilot study exploring the use of artificial intelligence in reversing a bilingual dictionary. The Modern Icelandic-English Dictionary is a freely available online resource. The aim was to transform this Icelandic-English dictionary into a functional English-Icelandic dictionary while minimising manual labour. Using the DANTE English lexical database as a reference, the...

100. Effectiveness of AI for the Lexicography of Low-Resource Languages: The Dictionary of Georgian Neologisms

Tinatin Margalitadze (Ilia State University), Giorgi Meladze (Ilia State University), Ketevan Mchedlishvili (Ilia State University), Tamar Laluashvili (Ilia State University), Giorgi Okropiridze (Ilia State University)

02/10/2026, 09:40

The purpose of this paper is to present the results of a study investigating the effectiveness of AI in the compilation of the Dictionary of Georgian Neologisms, an ongoing project at the Centre for Lexicography and Language Technologies at Ilia State University. The data for the study were selected from a dataset of 1,700 neologisms identified in previous research that developed a...

131. A Hybrid Approach to Web Accessibility Evaluation in Digital Lexicography: Comparing and Integrating Rule-Based Validators and Generative AI

Jesús Torres del Rey (University of Salamanca), M.ª Teresa Fuentes Morán (University of Salamanca)

02/10/2026, 14:00

Electronic dictionaries pose particular accessibility challenges for blind screen reader users, yet the field lacks evaluation frameworks that account for the complexity of their information structures. This paper reports on a three-phase study comparing Automated Web Accessibility Evaluation Tools and Large Language Models in evaluating three online dictionary entries from different...

132. Divide and Define with LLMs: Generating Definitions for the Digital Dictionary Database of Slovene

Iztok Kosem (University of Ljubljana & Jožef Stefan Institute), Polona Gantar (University of Ljubljana, Faculty of Arts & Faculty of Computing and Information Science), Simon Krek (Jožef Stefan Institute), Tjaša Arčon (University of Ljubljana, Faculty of Computing and Information Science)

02/10/2026, 14:30

This paper presents an experiment on generating definitions for Slovene headwords using four Large Language Models (LLMs): two commercial (Gemini and GPT) and two open-source (Gemma and the Slovenian model GaMS). Each model was provided with contextual data, including semantic indicators, collocations, and examples. We tested a zero-shot approach and two few-shot approaches using sample...

133. LLM-Assisted Lexicography in Low-Resource Contexts: From Prompt to Dictionary Article

Katharina Korecky-Kröll (Austrian Academy of Sciences, ACDH), Philipp Stöckle (Austrian Academy of Sciences, ACDH), Daniel Elsner (Austrian Academy of Sciences, ACDH), Wolfgang Koppensteiner (Austrian Academy of Sciences, ACDH), Elisabeth Eder (Austrian Academy of Sciences, ACDH)

02/10/2026, 15:00

This paper investigates the potential of Large Language Models (LLMs) to support lexicographic work in low-resource contexts, focusing on Austrian Bavarian dialects documented in the Wörterbuch der bairischen Mundarten in Österreich (WBÖ). Using a structured prompt-engineering workflow and a three-stage data pipeline, 100 dictionary articles were generated with LLaMA 4 (Scout) and...

140. Affordance Norms in Czech and English: Human-LLM Misalignment in Embodied Lexical Knowledge

Martina Vokáčová (Charles University), Anna Marklová (Charles University)

02/10/2026, 16:00

This paper investigates whether large language models can capture the embodied dimension of word meaning by comparing LLM-generated affordance norms with human-produced norms in Czech and English. Affordance norms are systematically collected data on the actions speakers associate with concrete objects. Human data were collected from 30 Czech native speakers in a free-production experiment...

141. Agree to Disagree: Intra-Annotator Agreement in Semi-Automatic Vocabulary Building

František Kovařík (Lexical Computing), Marek Blahuš (Lexical Computing), Miloš Jakubíček (Lexical Computing), Vojtěch Kovář (Lexical Computing)

02/10/2026, 16:30

Intra-annotator agreement is the rate at which an annotator makes the same choices in the same situation. This paper examines the annotation process in a semi-automatic dictionary-making project, Czech Dictionary Express. In the vocabulary-building process, its annotators went through 100,000 headwords from a corpus frequency wordlist, marking each as incorrect or (partially) correct. The aim...

142. Are Bears More Offensive than Dogs When Drunk? Using LLMs to Systematize the Labelling of Estonian Synonyms

Lydia Risberg (Estonian Language Institute, University of Tartu), Kristina Koppel (Estonian Language Institute), Margit Langemets (Estonian Language Institute), Hanna Maask (Estonian Language Institute), Esta Prangel (Estonian Language Institute), Maria Tuulik (Estonian Language Institute), Silver Vapper (Estonian Language Institute)

03/10/2026, 09:00

This paper investigates the potential of large language models (LLMs) as assistants with corpus analysis in lexicography, focusing on the assignment of register labels in the EKI Combined Dictionary (CombiDic). Inconsistencies in register labels become evident across synonym sets in CombiDic, which is the result of different lexicographers working on words at different times. We examine how...

143. The Integration of British and American Slang in Contemporary Polish and the Role of LLM-Driven Dynamic Lexicography

Barbara Lewandowska-Tomaszczyk (University of Applied Sciences in Konin)

03/10/2026, 09:30

This paper investigates the accelerating influx of English slang into the Polish language, driven by digital globalization and social media usage. While historical Anglicisms often focused on technical or professional domains, modern borrowing increasingly penetrates the affective realm—informal expressions of identity, emotion, and subcultural belonging. Central to this exploratory research...

144. Reflections on the Semantic Understanding of Generative AI: From LLM Experiments to Lexicographical Tools

Ines Röhrer (Bavarian Academy of Sciences and Humanities), Manuel Raaf (Bavarian Academy of Sciences and Humanities)

03/10/2026, 10:00

This article presents an application evaluation of the use of large language models (LLMs) for the semantic classification of lexicographical content in three German dialect dictionary projects. Building on earlier experiments with LLM-based semantic classification that showed hit rates of over 80%, the study investigates whether generative AI can support the assignment of meanings to...

145. Introducing Human-Centeredness in AI-Assisted Lexicography

Antonio San Martín (University of Quebec in Trois-Rivières), Catherine Trekker (University of Quebec in Trois-Rivières)

03/10/2026, 10:30

This paper proposes a human-centered artificial intelligence (HCAI) framework for AI-assisted lexicography. While generative AI offers significant opportunities to enhance lexicographic work, it also raises concerns regarding the future role of lexicographers and the preservation of linguistic and cultural diversity. Drawing on HCAI principles and previous applications in other language...