DETECH 2026, the DEfinition and Term Extraction Challenge, organized as part of the HEREDITARY project, will take place on June 24, 2026, at University of Zadar, Croatia, as a hybrid satellite event of MDTT 2026, Multilingual Digital Terminology Today: Design, representation formats and management systems.
The training data for DETECH 2026 is now available in GitHub, and the challenge is officially open to participation. We welcome anyone interested in automatic term extraction, definition generation, biomedical NLP, and medical terminology to take part in the event. Teams and individual researchers can register until March 13, 2026, and start experimenting with the dataset ahead of the evaluation phase.
What is DETECH?
DETECH focuses on automatic extraction of domain-specific terms and the generation of natural language definitions for medical concepts. The 2026 edition will focus on the gut–brain interplay, offering a real-world testbed for NLP methods in gastroenterology, neuroscience, and genetics.
Challenge Tasks
The challenge features two main tasks:
- Task A – Term Extraction: Identify relevant single-word and multi-word terms from English texts on the gut–brain axis.
- Task B – Definition Generation: Create natural language definitions for the extracted concepts, using corpus-based evidence or automatic text generation techniques.
Key dates for DETECH 2026
- January 22: Training data release
- March 13: Registration deadline for participation
- March 20: Test data release
- March 27: Submission of runs
- April 7: Submission of reports
- April 15: Results announced
- April 21: Review feedback
- May 15: Camera-ready report submission
- June 15: Registration deadline for the event
- June 24: Day of the challenge
Who Can Participate?
Researchers, academics, and industry teams working in NLP, biomedical informatics, terminology, or lexicography. Each team can submit up to five runs per subtask and external resources such as pre-trained models, lexicons, or ontologies are allowed but must be properly documented. Manual runs are also accepted but will not be ranked.
Submissions & Evaluation
All submissions must include a technical report detailing the approach, experiments, and results. Reports will be peer-reviewed and published in the CEUR-WS online open-access platform, which is indexed in Scopus. Accepted papers can later be extended for submission to journals or edited volumes, providing further visibility for participants’ research.
What is MDTT 2026?
The “Multilingual Digital Terminology Today: Design, Representation Formats and Management Systems” (MDTT 2026) is the fifth international conference dedicated to the design, representation, and management of digital terminology resources. This event focuses on methods for analyzing user needs, designing and validating terminological resources, and developing effective representation formats and management systems.
Stay tuned for registration details and submission instructions, which will soon be available. We look forward to seeing you at DETECH 2026, where innovation in explainable, data-driven medical terminology meets cutting-edge NLP research!
Recent Comments