eLex 2025

Session

Parallel sessions 1 (Arnold hall)

Nov 18, 2025, 11:00 AM

Arnold hall

Conveners

Parallel sessions 1 (Arnold hall)

• Tanara Zingano Kuhn

Parallel sessions 1 (Arnold hall)

• Jaka Čibej

Parallel sessions 1 (Arnold hall)

• Kristina Kocijan

Parallel sessions 1 (Arnold hall)

• Kristina Kocijan

Parallel sessions 1 (Arnold hall)

• Ivana Filipović Petrović

Parallel sessions 1 (Arnold hall)

• Kristina Koppel

Parallel sessions 1 (Arnold hall)

• Carole Tiberius

Parallel sessions 1 (Arnold hall)

• Jelena Kallas

9. Retention of English words from interaction with dictionaries and GenAI Chatbots

Mr Robert Lew, Bartosz Ptasznik

11/18/25, 11:00 AM

The public release of ChatGPT in late 2022 made an impact on many professional domains. Notwithstanding the many controversies surrounding Generative Artificial Intelligence (GenAI), such as ethics, copyright, accountability, or ecology, we need to acknowledge an important and relevant feature of Large Language Models and chatbot systems built around them: their ability to produce mostly...

10. Automating Adjectival Microstructures in Monolingual Dictionaries: A New Method Combining Embeddings and LLMs

Enikő Héja, László Simon, Veronika Lipp

11/18/25, 11:30 AM

Recent findings indicate that current large language models (LLMs) face difficulties in generating clear-cut, well-motivated definitions in a consistent way. This shortcoming is the consequence of their reliance on opaque data sources and their inherently unstable, non-deterministic outputs. In response, this research aims to develop an LLM-based methodology for producing adjectival...

11. 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

11/18/25, 12:00 PM

Finding non-recorded senses is important for dictionary maintenance, where using automatic methods helps reduce manual efforts. We use automatic Word Sense Induction (WSI) to compare recorded sense numbers among a sample of headwords in a comprehensive Swedish monolingual dictionary with induced sense numbers for the same words in a Swedish corpus. We propose this as a simple technique to find...

12. Automatic Detection of Word Sense Shift from Corpus Data

Ondřej Herman

11/18/25, 12:30 PM

Language evolves continuously, rendering static dictionaries quickly outdated. While previous research has addressed the automatic detection of new words, identifying subtler semantic changes in existing words remains a challenge. In this work, we propose a robust, language-independent methodology for the automatic detection of word sense shifts using diachronic corpus data. Our approach...

30. The Dictionary of Contemporary Serbian Language (RSSJ): Advanced Automation and Other Challenges

Ranka Stanković, Rada Stijović, Mihailo Škorić, Cvetana Krstev

11/18/25, 2:30 PM

This paper introduces the Dictionary of Contemporary Serbian Language (RSSJ), an ongoing large-scale digital lexicographic project designed to serve both human users via web and mobile applications and machines through APIs. Coordinated by the diaspora association “Gathered around the Language” and the Society for Language Resources and Technologies (JeRTeh), RSSJ aims to produce a dictionary...

31. 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

11/18/25, 3:00 PM

Large Language Models (LLMs) tend to expose severe language and cultural biases when working in medium- and low-resourced languages. In this paper, we present our work on Danish benchmarking and evaluation of LLMs to more precisely diagnose and potentially remedy such bias. To this aim, we apply available lexical-semantic resources to compile a set of Natural Language Understanding (NLU) tasks...

32. 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

11/18/25, 3:30 PM

The use of corpora is well established in lexicography, also in Estonia, but since the analysis of corpus data and the post-editing of automatically generated data from the corpus is labour-intensive, the use of large language models (LLMs) has led to growing interest in lexicography (e.g., Evert et al. 2024; Kosem, Gantar et al. 2024; Tiberius et al. 2024). In 2024, the Institute of the...

40. The lemma dilemma, Slovene version

Polona Gantar, Cyprian Laskowski, Simon Krek

11/19/25, 10:05 AM

In lexicography, one of the long-standing issues is understanding the nature of its core element of description commonly referred to as the headword (in DMLex and traditional lexicography), canonical form (in OntoLex and the Lexical Markup Framework – LMF), orthographic form (in the Text Encoding Initiative – TEI Lex0), lemma (in Wikidata), or lexical unit. With the transition from paper to...

43. Making Sense of the Past: AI-Assisted Historical Word Sense Disambiguation and the OED

Elinor Hawkes, Phoebe Nicholson, Will Rogers

11/19/25, 11:00 AM

This paper presents the Oxford English Dictionary’s (OED) current exploration into the application of artificial intelligence to historical Word Sense Disambiguation (WSD), a fundamental aspect of OED’s core research. Building on a longstanding tradition of technological innovation, the OED is investigating how Large Language Models (LLMs) can support the identification and retrieval of...

44. Bridging human and AI perspectives: semantic annotation of generic nouns in German

Iván Arias-Arias, Elena Martín-Cancela

11/19/25, 11:30 AM

Generic nouns such as Sache and Ding pose a challenge for semantic annotation due to their referential underspecification and context-dependent meaning. Although frequently classified under categories like {artefact} or {object}, their actual referents often belong to abstract or cognitive domains, as in Der Placeboeffekt ist eines der faszinierendsten Dinge in der Welt der Medizin. Drawing on...

49. Choosing Suitable Text Corpora for Identifying Collocations – A Case Study of a Large Reference Dictionary of Contemporary German

Luise Köhler, Gregor Middell, Alexander Geyken

11/19/25, 2:30 PM

Collocations are a well-covered research area in lexicography. With the advent of evidence-based lexicography and the availability of large text corpora, computational methods of extracting typical co-occurrences from such corpora and supporting lexicographers in identifying collocations among them became a research focus. Especially the statistical properties of collocations (i.e. application...

50. 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

11/19/25, 3:00 PM

Language corpora have long been used in linguistics and lexicography, but recent developments now allow large language models (LLMs) to support or even transform these fields. This study investigates the potential of LLMs for annotating informal language use in Estonian – a language underrepresented in LLM training data yet supported by a large corpus. Focusing on the informal register label...

51. So Close but Still Far: Case Study on Application of LLMs in Idioms Identification, Definition, and Generation of Illustrative Examples

Aleksandra Marković, Ranka Stanković

11/19/25, 3:30 PM

Automation has revolutionised lexicography, introducing the ’post-editing lexicography’ model, where the role of the lexicographer involves refining automatically generated dictionary drafts. Since the launch of ChatGPT in November 2022, numerous papers have explored the potential applications of LLMs in dictionary production. The rapid evolution of LLMs necessitates a re-evaluation of...

58. How Effective is AI as a Language Consultant?

Urška Vranjek Ošlak

11/19/25, 4:30 PM

This paper explores the applicability of generative artificial intelligence in the field of language consulting, focusing on ChatGPT-4 and the Slovenian language. The analysis is based on an experiment involving 30 real user questions submitted to the Language Consulting Service (LCS) of the Fran Ramovš Institute of the Slovenian Language. The questions cover a range of linguistic categories...

59. Corpus-Based Vocabulary Profiling for Ukrainian: From Lexical Analysis to the PULS Digital Learning Platform

Olena Synchak, Vasyl Starko, Mariana Burak, Mykhaylo Svystun

11/19/25, 5:00 PM

While CEFR-aligned vocabulary profiles have been developed for many languages (e.g., English, German, and Swedish), Ukrainian as a foreign language (UFL) still lacks an empirically grounded lexical profile. A foundational issue in creating such profiles is combining lexical frequency data with expert knowledge to assign CEFR-level labels. Existing UFL word lists rely primarily on professional...

60. Identifying the Most Representative Phraseological Units Using Language Corpora and Artificial Intelligence for Lexicography: The Case of Slovenian Comparative Phrasemes

Matej Meterc, Nataša Jakop

11/19/25, 5:30 PM

In preparing phraseological units for the third edition of the Standard Slovenian Dictionary (eSSKJ), the authors aimed to identify the most relevant comparative phrasemes in the contemporary standard language using objective corpus-based criteria. A key goal was to determine how representative specific phrasemes and their variants are in actual use. Two lists of the hundred most frequent...

68. Contrasting a new AI-powered dictionary designed for on-screen reading with electronic dictionaries that have evolved from print editions

Ana Frankenberg-Garcia

11/20/25, 10:05 AM

The use of LLMs in lexicography is a hot topic and indeed the focus of eLex 2025. In the past couple of years, several papers have emerged comparing existing dictionary entries with zero-shot chatbot queries (e.g. Nichols 2023) or with dictionary-like content obtained through the dynamic interaction between experts and chatbots (e.g. Lew 2023, Jakubíček & Rundell 2023). However, studies so far...

71. DMLEX on Wikibase: Legacy dictionaries as collaboratively editable dataset

Simon Krek, Primož Ponikvar, Andraž Repar, Iztok Kosem, David Lindemann

11/20/25, 11:00 AM

This paper presents an experimental workflow for converting legacy digitized dictionaries into the DMLex standard and subsequently importing them into a Wikibase instance. DMLex, a serialization-independent model developed by the OASIS LEXIDMA Technical Committee, aims to provide a universal and modular representation of lexicographic data. The study tested whether dictionaries from...

72. Image-to-Sense Alignment Using AI Tools

Andrej Perdih, Dejan Gabrovšek, Janoš Ježovnik

11/20/25, 11:30 AM

This paper evaluates the results of using GPT-4o mini language model batch processing with image recognition capability to align 1,572 images of 398 polysemous nouns in the Dictionary of the Slovenian Standard Language (second edition) to their specific dictionary senses, and it compares them to the results of the manual image-to-sense alignment process. The images were manually assigned to...

73. 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

11/20/25, 12:00 PM

Representative monitor corpora with detailed metadata offer a solid empirical basis for documenting lexical innovation and change (Kosem et al. 2021). However, continuously updated time-stamped textual data presents challenges for data management, lexicographic analysis, and visualization. Building on its existing corpus infrastructure, the Dutch Language Institute (INT) has developed...