36.3228, Confs: Definition and Term Extraction Challenge (Croatia)

[The LINGUIST List]

LINGUIST List: Vol-36-3228. Fri Oct 24 2025. ISSN: 1069 - 4875.

Subject: 36.3228, Confs: Definition and Term Extraction Challenge (Croatia)

Moderator: Steven Moran (linguist at linguistlist.org)
Managing Editor: Valeriia Vyshnevetska
Team: Helen Aristar-Dry, Mara Baccaro, Daniel Swanson
Jobs: jobs at linguistlist.org | Conferences: callconf at linguistlist.org | Pubs: pubs at linguistlist.org

Homepage: http://linguistlist.org

Editor for this issue: Valeriia Vyshnevetska <valeriia at linguistlist.org>

================================================================


Date: 22-Oct-2025
From: Giorgio Maria Di Nunzio [giorgiomaria.dinunzio at unipd.it]
Subject: Definition and Term Extraction Challenge


Definition and Term Extraction Challenge
Short Title: DETECH 2026

Date: 24-Jun-2026 - 24-Jun-2026
Location: Zadar, Croatia
Meeting URL: https://detech2026.dei.unipd.it/

Linguistic Field(s): Computational Linguistics
Subject Language(s): English (eng)
Language Family(ies): English based

Submission Deadline: 07-Apr-2026

Evaluation Task co-located with Multilingual Digital Terminology Today
(MDTT) 2026
Official Website:  https://detech2026.dei.unipd.it/
Overview:
The DEfinition and Term Extraction Challenge (DETECH) focuses on the
automatic extraction of domain-specific terminology and the generation
of clear, context-aware definitions in Italian medical discourse.
Organized within the HEREDITARY project, DETECH inaugurates a new
evaluation challenge dedicated to the intersection of terminology,
NLP, and biomedical text analysis. It will take place as a satellite
workshop of Multilingual Digital Terminology Today (MDTT) 2026,
scheduled for June 24, 2026.
This first edition explores the gut–brain interplay, a domain at the
crossroads of gastroenterology, neuroscience, and genetics. It
provides a realistic testbed for evaluating automatic methods that
identify and describe specialized concepts in complex medical
communication.
DETECH aims to advance research on explainable, data-driven medical
terminology by combining term extraction and definition generation
into a unified challenge.
Subtasks:
 - Subtask A – Term Extraction:
Identify relevant single-word and multi-word terms from Italian texts
concerning the gut–brain interplay.
 - Subtask B – Definition Generation:
Produce clear and informative definitions for the extracted terms,
using corpus-based evidence or automatic text generation methods.
Participants may join one or both subtasks.
Participation:
We welcome participation from academic, research, and industry teams
working in NLP, terminology, biomedical informatics, or lexicography.
 - Up to five runs per subtask per team are allowed.
 - External resources (e.g., pre-trained models, lexicons, ontologies)
are permitted but must be clearly documented.
 - Manual runs are accepted but will not be ranked.
 - Registration details will be available on the task website.
Evaluation:
 - Subtask A: Micro-F1 (how consistently systems detect terms across
the corpus) and Type-F1 (how well they capture the domain’s conceptual
terminology) term identification.
 - Subtask B: BLEU, BERTScore and additional manual evaluation for
evaluating the informativeness and linguistic quality of definitions.
Baseline systems and evaluation scripts will be released along with
the training data.
Submission of Technical Reports:
Participants must submit a technical report describing their approach,
experiments, and results that will be published on the CEUR-WS
proceedings.
Each report should include:
 - Methodology and theoretical framework
 - Data preprocessing and system description
 - Experimental setup and results
 - Comparison with baselines
 - Analysis and discussion of findings
Timeline:
Jan 15, 2026 - Training data release
Mar 13, 2026 - Participation deadline
Mar 20, 2026 - Test data release
Mar 27, 2026 - Submission of runs
Apr 7, 2026 - Submission of reports
Apr 15, 2026 - Results announced
Apr 21, 2026 - Review feedback
May 15, 2026 - Camera-ready report submission
June 15, 2026 - Registration deadline
June 24, 2026 - DETECH Workshop @ MDTT 2026
Organizers:
Federica Vezzani, University of Padova, Italy
Giorgio Marira Di Nunzio, University of Padova, Italy
Vanessa Bonato, University of Padova, Italy
Gianmaria Silvello, University of Padova, Italy



------------------------------------------------------------------------------

********************** LINGUIST List Support ***********************
Please consider donating to the Linguist List, a U.S. 501(c)(3) not for profit organization:

https://www.paypal.com/donate/?hosted_button_id=87C2AXTVC4PP8

LINGUIST List is supported by the following publishers:

Bloomsbury Publishing http://www.bloomsbury.com/uk/

Cambridge University Press http://www.cambridge.org/linguistics

Cascadilla Press http://www.cascadilla.com/

De Gruyter Brill https://www.degruyterbrill.com/?changeLang=en

Edinburgh University Press http://www.edinburghuniversitypress.com

John Benjamins http://www.benjamins.com/

Language Science Press http://langsci-press.org

Lincom GmbH https://lincom-shop.eu/

MIT Press http://mitpress.mit.edu/

Multilingual Matters http://www.multilingual-matters.com/

Narr Francke Attempto Verlag GmbH + Co. KG http://www.narr.de/

Netherlands Graduate School of Linguistics / Landelijke (LOT) http://www.lotpublications.nl/

Peter Lang AG http://www.peterlang.com


----------------------------------------------------------
LINGUIST List: Vol-36-3228
----------------------------------------------------------