The following workshops are offered as part of EURALEX 2026:
The 8th Globalex Workshop on Lexicography and Neology (GWLN-8)
Organisers
Ilan Kernerman (Lexicala by K Dictionaries) and Kris Heylen (Dutch Language Institute)
Description
In recent years, the Globalex Workshop on Lexicography and Neology series (GWLN) has evolved into an international forum for lexicographers, scholars, tool developers, and other practitioners interested in how new words and new senses emerge, are detected, are evaluated as candidates for inclusion, and described in lexicographic resources. Since its inauguration, the workshop has taken place in seven consecutive years in conjunction with annual conferences of the continental lexicography associations, including DSNA (2019), Euralex (2020 online, and 2022), Australex (2021), Asialex (2023), Afrilex (2024), as well as at eLex (2025). Each edition has brought together participants from diverse linguistic traditions – covering both high- and low-resource languages – to share their experience and exchange perspectives on the challenges, methodologies and processes for combining lexicography and neology. For the eighth iteration, GWLN is teaming up with the European Network on Lexical Innovation (ENEOLI COST Action) to further strengthen collaboration in Europe and beyond.
The main topic of GWLN-8 will be the shifting role of the lexicographer in the age of artificial intelligence (AI). While lexicography has always been an early adopter of technological advances in linguistics, corpus analysis, and dictionary production workflows, recent developments in large and custom language models and generative AI have fundamentally altered the ecology of lexical innovation, its description, and the possibilities for lexicographers. Neologisms now emerge and circulate not only through human linguistic communities, but also through AI-mediated content creation, algorithmic feedback loops, and hybrid forms of human–machine discourse. At the same time, AI-based technologies create new opportunities for lexicographers to automate detection pipelines, evaluate usage patterns, and compile entries grounded in different types of linguistic evidence and linked to highly structured lexical knowledge bases. Against this backdrop, the 2026 workshop will invite participants to reflect on lexicography’s mediating role between corpus-based empirical evidence, AI-generated content, and the need for reliable, curated and structured lexicographic data that can feed back into and support the emerging hybrid ecosystem of AI-enhanced human communication.
Besides publication in conference proceedings, GWLN papers have formed Special Issues of Dictionaries. Journal of the Dictionary Society of North America (2020), International Journal of Lexicography (2021), Lexicographica. Series Maior (2022), Lexicography. Journal of Asialex (2023), and a special section of Lexikos (2025). Selected GWLN-8 papers will be published in the form of a special issue of International Journal of Lexicography in 2027.
Constructicography in Practice: Constructions, Challenges, and Opportunities
Organisers
Voula Giouli (Aristotle University of Thessaloniki, Greece), Athina Sioupi (Aristotle University of Thessaloniki, Greece), Nina Böbel (Heinrich Heine University Düsseldorf, Germany), Alexander Ziem (Heinrich Heine University Düsseldorf, Germany)
Description
Constructicography (Lyngfelt et al. 2008), the systematic description of constructions in Constructicons and construction-based lexicographic resources, has emerged as a key area at the intersection of Construction Grammar (i.e., Croft 2001), lexicography, and computational linguistics. While constructions have long been acknowledged as central units of linguistic knowledge, their consistent representation, annotation, and integration into lexicographic resources remain methodologically and technologically challenging.
The proposed workshop aims to bring together researchers working on theoretical, descriptive, and computational aspects of constructicography. It will focus on how constructions are identified, modeled, represented, and linked to lexical, semantic, and pragmatic information across languages and resource types. Particular attention will be paid to challenges such as construction granularity, variation, productivity, cross-linguistic comparability, corpus-driven discovery, and interoperability with existing lexical resources.
At the same time, the workshop highlights emerging opportunities offered by large corpora, annotation frameworks, and NLP techniques, including construction mining, semi-automatic Constructicon building, and the use of large language models in constructional analysis. Moreover, the workshop will explore applications of Constructicons, particularly in language teaching and learning.
By fostering dialogue between linguists, lexicographers, educational experts and computational researchers, the workshop seeks to advance constructicography as a mature and practically applicable field within lexicography.
References
Croft, W. (2001). Radical Construction Grammar. Syntactic theory in typological perspective. Oxford/New York: Oxford University Press. doi: 10.1093/acprof:oso/9780198299554.001.0001
Lyngfelt, B., Borin, L., Ohara, K. and Torrent, T., and Timponi, T.T. (2018) Constructicography: Constructicon development across languages, John Benjamins Publishing Company, 2018. https://doi.org/10.1075/cal.22
Postediting lexicography with Sketch Engine and Lexonomy
Organiser
Ondřej Matuška (Sketch Engine)
Description
The tutorial aims to promote the understanding of state-of-the-art lexicographic practices based on the post-editing of corpus-generated and AI-generated content. It focuses on how contemporary lexicography can effectively combine automation with expert human judgement to achieve efficient, scalable, and cost-effective editorial workflows while ensuring that all dictionary data remain fully reviewed and validated by human editors.
The workshop provides an overview of current corpus and AI technologies relevant to dictionary making. Sketch Engine ( https://www.sketchengine.eu/ ) is exploited to support key lexicographic tasks such as sense analysis, collocation extarction, example selection, and pattern discovery. The session will also introduce Lexonomy ( https://guide.lexonomy.eu/ ) as a modern dictionary writing system designed for updating legacy dictionaries as well as creating new lexicographic works. Lexonomy demonstrates how corpus evidence and post-edited content can be efficiently structured, edited, and published within a collaborative editorial environment.
A central component of the tutorial is the presentation of the Dictionary Express method ( https://dictionary.express/ ), which combines automated content generation with systematic post-editing to accelerate dictionary production without compromising quality. Through practical workflows and concrete examples, the tutorial will show how corpus data, AI-assisted suggestions, and editorial guidelines can be integrated into a coherent process that supports consistency, transparency, and editorial control. The session is intended for lexicographers, editors, and researchers interested in applying corpus-based and AI-supported methods to contemporary dictionary projects.
Multi-word expressions and phraseology: corpus-based and computer-processed
Organisers
Lian Chen (Laboratoire LLL, University of Orléans & CRLAO–CNRS–INALCO, France), Besim Kabashi (Eberhard Karls Universität Tübingen, Germany)
Description
Phraseology (Cowie 1998; Granger & Meunier 2008; Mitkov 2017; Mel’čuk 2023; Polguère, 2002, 2014; Mejri 2018; Chen 2021), or multiword expressions (MWEs) (Savary 2008; Constant 2012) occupy a central position in linguistic description, language use, and language learning. Idioms, collocations, lexical bundles, and fixed or semi-fixed expressions constitute a significant part of natural language, yet they remain challenging to model, describe, and represent in lexicographic resources (Pecina, P. 2010; Mel’čuk 2011, Polguère 2014, Chen 2025). With the rapid development of new technologies—particularly corpus linguistics, Natural Language Processing (NLP), and Artificial Intelligence (AI)—phraseology and lexicography are currently undergoing a profound methodological and conceptual transformation.
From a modeling perspective, new technologies make it possible to move beyond traditional, intuition-based descriptions of phraseological units. Large-scale corpora (Mitkov 2017), both general and specialized, enable the systematic identification of MWEs through statistical, distributional, and syntactic approaches. Methods such as n-gram extraction, association measures (PMI, t-score), syntactic patterning, and embedding-based similarity allow researchers to capture degrees of fixedness, semantic compositionality, and contextual variability. These advances open new perspectives for representing phraseological knowledge in structured models, including ontologies, lexical networks, and standards such as OntoLex-Lemon (McCrae, Bosque-Gil et al. 2017 ; Bosque-Gil et al. 2019).
In terms of resource creation, technological tools have profoundly reshaped lexicographic practices (Atkins & Rundell 2008; Granger & Paquot 2012). Digital corpora, web-based data, and annotation platforms facilitate the semi-automatic extraction and validation of phraseological units (Mitkov 2017; Evert 2008; Gries 2008; Constant et al. 2017). New-generation lexical resources integrate rich metadata, usage examples, frequency information, and semantic relations, making them more dynamic and interoperable (Polguère 2014; Ci-miano et al. 2016; McCrae et al. 2017).. Moreover, computational approaches enable the development of multilingual and contrastive resources, which are essential for studying phraseological variation across languages and cultures (Paquot 2015; Mel’čuk 2011).
New technologies also play a crucial role in the design of pedagogical dictionaries and lear-ning-oriented resources (Bogaards & van der Kloot 2002; Lew 2012). Phraseology is often a major obstacle for language learners, as MWEs cannot always be interpreted compositionally (Wray 2002; Howarth 1998; Granger 1998). Corpus-based examples, learner-oriented definitions, and adaptive digital interfaces can significantly enhance the accessibility and usability of phraseological information (Sinclair 2004; Granger & Paquot 2015; Paquot 2015). AI-driven tools, such as intelligent tutoring systems or LLM-assisted lexicography, offer promising avenues for generating contextualized examples, usage notes, and difficulty pro-files tailored to learners’ needs (Heift & Schulze 2007; Godwin-Jones 2023; Bender & Koller 2020).
In translation lexicography, the impact of new technologies is equally significant (Hartmann 2007; Atkins & Rundell 2008; Tarp 2012). Phraseological units pose well-known challenges in translation due to their idiomaticity and phraseocultural specificity (Chen 2022a; 2022b). Parallel corpora, alignment tools, and machine translation systems provide valuable data for identifying translation equivalents, partial correspondences, and translation strategies (Chen et al. 2024). Digital translation dictionaries can now incorporate cross-linguistic mappings, semantic annotations, and real attested examples, bridging the gap between lexicographic description and actual translational practice.
Finally, the analysis of existing dictionaries through technological means (Béjoint 2010; Lew 2013) offers new insights into lexicographic traditions and practices. Computational methods allow for the large-scale comparison of dictionary entries, coverage, microstructure, and treatment of phraseological units. Such analyses contribute to a critical understanding of how dictionaries evolve in response to technological, linguistic, and societal changes (Hausmann 1989; Tarp 2012; Fuertes-Olivera & Bergenholtz 2011).
The intersection of phraseology, multi-word expressions, lexicography, and new technologies constitutes a fertile research domain, fostering innovative models, richer resources, and more effective tools for analysis, learning, and translation.