9:00–9:10 Opening Remarks
9:10–9:30 Findings of the VarDial Evaluation Campaign 2025: The NorSID Shared Task on Norwegian Slot, Intent and Dialect Identification – Yves Scherrer, Rob van der Goot and Petter Mæhlum
9:30–9:50 Shared Task Participants Poster Boosters (5 minutes per poster)
HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation – Jaione Bengoetxea, Mikel Zubillaga, Ekhi Azurmendi, Maite Heredia, Julen Etxaniz, Markel Ferro and Jeremy Barnes
LTG at VarDial 2025 NorSID: More and Better Training Data for Slot and Intent Detection – Marthe Midtgaard, Petter Mæhlum and Yves Scherrer
Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection – Verena Blaschke, Felicia Körner and Barbara Plank
CUFE@VarDial 2025 NorSID: Multilingual BERT for Norwegian Dialect Identification and Intent Detection – Michael Ibrahim
9:50–10:15 Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study – Xaver Maria Krückl, Verena Blaschke and Barbara Plank
10:15–10:25 Poster Boosters (5 minutes per poster)
Adapting Whisper for Regional Dialects: Enhancing Public Services for Vulnerable Populations in the United Kingdom – Melissa Torgbi, Andrew Clayman, Jordan J. Speight and Harish Tayyar Madabushi
Regional Distribution of the /el/-/æl/ Merger in Australian English – Steven Coats, Chloé Diskin-Holdaway and Debbie Loakes
10:30–11:00 Coffee Break
11:00–12:00 Invited Talk – Fajri Koto (MBZUAI): Language Technology for Dialectal Diversity in Low-Resource Languages: Insights from Southeast Asia
Low-resource languages often feature rich dialectal variations that reflect unique cultural and linguistic identities. Despite their importance, these variations are frequently overlooked in the development of language technologies, particularly in Southeast Asia, a region renowned for its linguistic diversity. This talk examines the current state of language technology for low-resource languages in the region, highlighting the challenges and reviewing previous efforts to improve multilingual representation for these underrepresented languages. Additionally, we present findings from a survey of native speakers of dialectal languages, offering valuable insights into their needs and priorities for creating practical and inclusive language technologies.
12:00–12:25 Poster Boosters (5 minutes per poster)
Large Language Models as a Normalizer for Transliteration and Dialectal Translation – Md Mahfuz Ibn Alam and Antonios Anastasopoulos
Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy – Alistair Plum, Tharindu Ranasinghe and Christoph Purschke
Learning Cross-Dialectal Morphophonology with Syllable Structure Constraints – Salam Khalifa, Abdelrahim Qaddoumi, Jordan Kodner and Owen Rambow
Leveraging Open-Source Large Language Models for Native Language Identification – Yee Man Ng and Ilia Markov
Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varieties – Javier A. Lopetegui, Arij Riabi and Djamé Seddah
12:30–14:00 Lunch Break
14:00–15:00 Poster Session
15:05–15:30 Testing the Boundaries of LLMs: Dialectal and Language-Variety Tasks – Fahim Faisal and Antonios Anastasopoulos
15:30–16:00 Coffee Break
16:00–16:25 Information Theory and Linguistic Variation: A Study of Brazilian and European Portuguese – Diego Alves
16:25–16:50 Retrieval of Parallelizable Texts Across Church Slavic Variants – Piroska Lendvai, Uwe Reichel, Anna Jouravel, Achim Rabus and Elena Renje
16:50–17:15 Neural Text Normalization for Luxembourgish Using Real-Life Variation Data – Anne-Marie Lutgen, Alistair Plum, Christoph Purschke and Barbara Plank
17:15–17:30 Closing Remarks