Parallel session 1: Language modelling and multilinguality

Room: Lääne-Euroopa

Chair: Jenny Kunz

10.40–11.05
Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks

Dan Saattrup Nielsen, Kenneth Enevoldsen and Peter Schneider-Kamp

11.05–11.30
Poro 34B and the Blessing of Multilinguality

Risto Luukkonen, Jonathan Burdge, Elaine Zosa, Aarne Talman, Ville Komulainen, Väinö Hatanpää, Peter Sarlin and Sampo Pyysalo

11.30–11.55
Prompt Engineering Enhances Faroese MT, but Only Humans Can Tell

Barbara Scalvini, Annika Simonsen, Iben Nyholm Debess and Hafsteinn Einarsson

Parallel session 2: Digital humanities

Room: Põhja-Euroopa

Chair: Andrius Utka

10.40–11.05

Modeling Multilayered Complexity in Literary Texts

Pascale Feldkamp, Márton Kardos, Kristoffer Nielbo and Yuri Bizzoni

11.05–11.30

Comparative analysis of optical character recognition methods for Sámi texts from the National Library of Norway

Tita Enstad, Trond Trosterud, Marie Iversdatter Røsok, Yngvil Beyer and Marie Roald

11.30–11.55

Evaluating LLM-Generated Explanations of Metaphors – A Culture-Sensitive Study of Danish

Bolette S. Pedersen, Nathalie Sørensen, Sanni Nimb, Dorte Haltrup Hansen, Sussi Olsen and Ali Al-Laith

Parallel session 3: Computational semantics

Room: Ida-Euroopa

Chair: Elisa Bassignana

10.40–11.05

Analyzing the Effect of Linguistic Instructions on Paraphrase Generation

Teemu Vahtola, Songbo Hu, Mathias Creutz, Ivan Vulić, Anna Korhonen, Jörg Tiedemann

11.05–11.30

Language of the Swedish Manosphere with Swedish FrameNet

Emilie Marie Carreau Francis

11.30–11.55

Opinion Units: Concise and Contextualized Representations for Aspect-Based Sentiment Analysis

Emil Häglund and Johanna Björklund

Parallel session 4: Language modelling and applications

Room: Lääne-Euroopa

Chair: Hafsteinn Einarsson

15.50–16.15

Small Languages, Big Models: A Study of Continual Training on Languages of Norway

David Samuel, Vladislav Mikhailov, Erik Velldal, Lilja Øvrelid, Lucas Georges Gabriel Charpentier, Andrey Kutuzov and Stephan Oepen

16.15–16.40

Aligning Language Models for Icelandic Legal Text Summarization

Þórir Hrafn Harðarson, Hrafn Loftsson and Stefán Ólafsson

16.40–17.05

NorEventGen: generative event extraction from Norwegian news

Huiling You, Samia Touileb, Erik Velldal and Lilja Øvrelid

17.05–17.30

The Impact of Copyrighted Material on Large Language Models: A Norwegian Perspective

Javier de la Rosa, Vladislav Mikhailov, Lemei Zhang, Freddy Wetjen, David Samuel, Peng Liu, Rolv-Arild Braaten, Petter Mæhlum, Magnus Breder Birkenes, Andrey Kutuzov, Tita Enstad, Hans Christian Farsethås, Svein Arne Brygfjeld, Jon Atle Gulla, Stephan Oepen, Erik Velldal, Wilfred Øst-gulen, Lilja Øvrelid and Aslak Sira Myhre

Parallel session 5: Text classification and NER

Room: Põhja-Euroopa

Chair: Barbara Scalvini

15.50–16.15

Temporal Relation Classification: An XAI Perspective

Sofia Elena Terenziani

16.15–16.40

Investigating the effectiveness of Data Augmentation and Contrastive Learning for Named Entity Recognition

Noel Chia, Ines Rehbein and Simone Paolo Ponzetto

16.40–17.05

The Devil’s in the Details: the Detailedness of Classes Influences Personal Information Detection and Labeling

Maria Irena Szawerna, Simon Dobnik, Ricardo Muñoz Sánchez and Elena Volodina

17.05–17.25

Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languages

Andrei Politov, Oleh Shkalikov, Rene Jäkel and Michael Färber

Parallel session 6: Benchmarking and evaluation

Room: Ida-Euroopa

Chair: Mike Zhang

15.50–16.15

Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations

Emil Nuutinen, Iiro Rastas and Filip Ginter

16.15–16.40

Entailment Progressions: A Robust Approach to Evaluating Reasoning Within Larger Discourse

Rishabh Shastry, Patricia Chiril, Joshua Charney and David Uminsky

16.40–17.05

How Well do LLMs know Finno-Ugric Languages? A Systematic Assessment

Hele-Andra Kuulmets, Taido Purason and Mark Fishel

17.05–17.30

SweClinEval: A Benchmark for Swedish Clinical Natural Language Processing

Thomas Vakili, Martin Hansson and Aron Henriksson

Room: 1st floor, lobby area

14.10–15.50

Chair: Jurgita Kapočiūtė-Dzikienė

Demo: Estonian isolated-word text-to-speech synthesiser

Indrek Kiissel, Liisi Piits, Heete Sahkai, Indrek Hein, Liis Ermus and Meelis Mihkla

Demo: Interactive maps for corpus-based dialectology

Yves Scherrer and Olli Kuparinen

The Roles of English in Evaluating Multilingual Language Models

Wessel Poelman and Miryam de Lhoneux

How to Tune a Multilingual Encoder Model for Germanic Languages: A Study of PEFT, Full Fine-Tuning, and Language Adapters

Romina Oji and Jenny Kunz

Predictability of Microsyntactic Units across Slavic Languages: A translation-based Study

Maria Kunilovskaya, Iuliia Zaitova, Wei Xue, Irina Stenger and Tania Avgustinova

Comparing Human and Machine Translations of Generative Language Model Evaluation Datasets

Sander Bijl de Vroe, George Stampoulidis, Kai Hakala, Aku Rouhe, Mark van Heeswijk and Jussi Karlgren

Mind the Gap: Diverse NMT Models for Resource-Constrained Environments

Ona de Gibert, Dayyán O’Brien, Dušan Variš and Jörg Tiedemann

Can summarization approximate simplification? A gold standard comparison

Giacomo Magnifico and Eduard Barbu

Applying and Optimising a Multi-Scale Probit Model for Cross-Source Text Complexity Classification and Ranking in Swedish

Elsa Andersson, Johan Falkenjack and Arne Jönsson

Constructions and Strategies in Universal Dependencies

Joakim Nivre

Question-parsing with Abstract Meaning Representation enhanced by adding small datasets

Johannes Heinecke, Maria Boritchev and Frédéric Herledan

Database of Latvian Morphemes and Derivational Models: ideas and expected results

Andra Kalnača, Tatjana Pakalne, Kristīne Levāne-Petrova

MorSeD: Morphological Segmentation of Danish and its Effect on Language Modeling

Rob van der Goot, Anette Jensen, Emil Allerslev Schledermann, Mikkel Wildner Kildeberg, Nicolaj Larsen, Mike Zhang and Elisa Bassignana

Playing by the Rules: A Benchmark Set for Standardized Icelandic Orthography

Bjarki Ármannsson, Hinrik Hafsteinsson, Jóhannes B. Sigtryggsson, Atli Jasonarson, Einar Freyr Sigurðsson and Steinþór Steingrímsson

GliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian

Aleksei Dorkin and Kairit Sirts

Diachronic Analysis of Phrasal Verbs in English Scientific Writing

Diego Alves

MC-19: A Corpus of 19th Century Icelandic Texts

Steinþór Steingrímsson, Einar Freyr Sigurðsson and Atli Jasonarson

Efficient Elicitation of Fictitious Nursing Notes from Volunteer Healthcare Professionals

Jesper Vaaben Bornerup and Christian Hardmeier

Empathy vs Neutrality: Designing and Evaluating a Natural Chatbot for the Healthcare Domain

Cristina Reguera-Gómez, Denis Paperno and Maaike H. T. de Boer

Parallel session 7: Machine translation

Room: Lääne-Euroopa

Chair: Yves Scherrer

10.20–10.45

Incorporating Target Fuzzy Matches into Neural Fuzzy Repair

Tommi Nieminen, Jörg Tiedemann and Sami Virpioja

10.45–11.10

Tokenization on Trial: The Case of Kalaallisut–Danish Legal Machine Translation

Esther Ploeger, Paola Saucedo, Johannes Bjerva, Ross Deans Kristensen-McLachlan and Heather Lent

11.10–11.35

Paragraph-Level Machine Translation for Low-Resource Finno-Ugric Languages

Dmytro Pashchenko, Lisa Yankovskaya and Mark Fishel

11.35–12.00

Rethinking Low-Resource MT: The Surprising Effectiveness of Fine-Tuned Multilingual Models in the LLM Age

Barbara Scalvini, Iben Nyholm Debess, Annika Simonsen and Hafsteinn Einarsson

Parallel session 8: Short paper session

Room: Põhja-Euroopa

Chair: Elena Volodina

10.20–10.40

How Aunt-Like Are You? Exploring Gender Bias in the Genderless Estonian Language: A Case Study

Elisabeth Kaukonen, Ahmed Sabir and Rajesh Sharma

10.40–11.00

Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs

Artem Fedorchenko and Tanel Alumäe

11.00–11.20

Train More Parameters But Mind Their Placement: Insights into Language Adaptation with PEFT

Jenny Kunz

11.20–11.40

Annotating and Classifying Direct Speech in Historical Danish and Norwegian Literary Texts

Ali Al-Laith, Alexander Conroy, Kirstine Nielsen Degn, Jens Bjerring-Hansen and Daniel Hershcovich

11.40–12.00

Mixed Feelings: Cross-Domain Sentiment Classification of Patient Feedback

Egil Rønningstad, Lilja Charlotte Storset, Petter Mæhlum, Lilja Øvrelid and Erik Velldal

Parallel session 9: Language modelling and bias

Room: Ida-Euroopa

Chair: Samia Touileb

10.20–10.45

FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering

Erik Henriksson, Otto Tarkka and Filip Ginter

10.45–11.10

SnakModel: Lessons Learned from Training an Open Danish Large Language Model

Mike Zhang, Max Müller-Eberstein, Elisa Bassignana and Rob van der Goot

11.10–11.35

Danoliteracy of Generative Large Language Models

Søren Vejlgaard Holm, Lars Kai Hansen and Martin Carsten Nielsen

11.35–12.00

Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings

Carolin M. Schuster, Maria-Alexandra Roman, Shashwat Ghatiwala and Georg Groh

Parallel session 10: Resources and evaluation

Room: Lääne-Euroopa

Chair: Jenna Kanerva

16.00–16.25

Benchmarking Abstractive Summarisation: A Dataset of Human-authored Summaries of Norwegian News Articles

Samia Touileb, Vladislav Mikhailov, Marie Ingeborg Kroka, Lilja Øvrelid and Erik Velldal

16.25–16.50

The BRAGE Benchmark: Evaluating Zero-shot Learning Capabilities of Large Language Models for Norwegian Customer Service Dialogues

Mike Riess and Tollef Emil Jørgensen

16.50–17.15

A Collection of Question Answering Datasets for Norwegian

Vladislav Mikhailov, Petter Mæhlum, Victoria Ovedie Chruickshank Langø, Erik Velldal and Lilja Øvrelid

Parallel session 11: Speech technology

Room: Põhja-Euroopa

Chair: Tanel Alumäe

16.00–16.25

Towards large-scale speech foundation models for a low-resource minority language

Yaroslav Getman, Tamás Grósz, Katri Hiovain-Asikainen, Tommi Lehtonen and Mikko Kurimo

16.25–16.50

Match ‘em: Multi-Tiered Alignment for Error Analysis in ASR

Phoebe Parsons, Knut Kvale, Torbjørn Svendsen and Giampiero Salvi

16.50–17.15

Does Preprocessing Matter? An Analysis of Acoustic Feature Importance in Deep Learning for Dialect

Lea Fischbach, Caroline Kleen, Lucie Flek and Alfred Lameli

Parallel session 12: Morphology and syntax

Room: Ida-Euroopa

Chair: Joakim Nivre

16.00–16.25

Surface-Level Morphological Segmentation of Low-resource Inuktitut Using Pre-trained Large Language Models

Mathias Stenlund, Hemanadhan Myneni and Morris Riedel

16.25–16.50

Comparative Concepts or Descriptive Categories: a UD Case study

Matthieu Pierre Boyer and Mathieu Dehouck

16.50–17.15

Dialectal treebanks and their relation with the standard variety: The case of East Cretan and Standard Modern Greek

Socrates Vakirtzian, Vivian Stamou, Yannis Kazos and Stella Markantonatou

Room: 1st floor, lobby area

14.20–16.00

Chair: Max Müller-Eberstein

Demo: Braxen 1.0

Christina Tånnander and Jens Edlund

Demo. OpusDistillery: A Configurable End-to-End Pipeline for Systematic Multilingual Distillation of Open NMT Models

Ona de Gibert, Tommi Nieminen, Yves Scherrer and Jörg Tiedemann

SweSAT-1.0: The Swedish University Entrance Exam as a Benchmark for Large Language Models

Murathan Kurfalı, Shorouq Zahra, Evangelia Gogoulou, Luise Dürlich, Fredrik Carlsson and Joakim Nivre

Generative AI for Technical Writing: Comparing Human and LLM Assessments of Generated Content

Karen de Souza, Alexandre Nikolaev and Maarit Koponen

An Icelandic Linguistic Benchmark for Large Language Models

Bjarki Ármannsson, Finnur Ágúst Ingimundarson and Einar Freyr Sigurðsson

Better Benchmarking LLMs for Zero-Shot Dependency Parsing

Ana Ezquerro, Carlos Gómez-Rodríguez and David Vilares

LAG-MMLU: Benchmarking Frontier LLM Understanding in Latvian and Giriama

Naome A. Etori, Arturs Kanepajs, Kevin Lu and Randu Karisa

Localizing AI: Evaluating Open-Weight Language Models for Languages of Baltic States

Jurgita Kapočiūtė-Dzikienė, Toms Bergmanis, Mārcis Pinnis

Got Compute, but No Data: Lessons From Post-training a Finnish LLM

Elaine Zosa, Ville Komulainen and Sampo Pyysalo

Margins in Contrastive Learning: Evaluating Multi-task Retrieval for Sentence Embeddings

Tollef Emil Jørgensen and Jens Breitung

BiaSWE: An Expert Annotated Dataset for Misogyny Detection in Swedish

Kätriin Kukk, Danila Petrelli, Judit Casademont, Eric J. W. Orlowski, Michal Dzielinski and Maria Jacobson

Hotter and Colder: A New Approach to Annotating Sentiment, Emotions, and Bias in Icelandic Blog Comments

Steinunn Rut Friðriksdóttir, Dan Saattrup Nielsen and Hafsteinn Einarsson

Towards a Derivational Semantics Resource for Latvian

Ilze Lokmane, Mikus Grasmanis, Agute Klints, Gunta Nešpore-Bērzkalne, Pēteris Paikens, Lauma Pretkalniņa, Laura Rituma, Madara Stāde, Evelīna Tauriņa

Adding Metadata to Existing Parliamentary Speech Corpus

Phoebe Parsons, Per Erik Solberg, Knut Kvale, Torbjørn Svendsen and Giampiero Salvi

Mapping Faroese in the Multilingual Representation Space: Insights for ASR Model Optimization

Dávid í Lág, Barbara Scalvini and Jon Gudnason

Assessed and Annotated Vowel Lengths in Spoken Icelandic Sentences for L1 and L2 Speakers: A Resource for Pronunciation Training

Caitlin Laura Richter, Kolbrún Friðriksdóttir, Kormákur Logi Bergsson, Erik Anders Maher, Ragnheiður María Benediktsdóttir and Jon Gudnason

Testing relevant linguistic features in automatic CEFR skill level classification for Icelandic

Isidora Glišić, Caitlin Laura Richter, Anton Karl Ingason

Transfer-Learning German Metaphors Inspired by Second Language Acquisition

Maria Berger

A Comparative Study of PEFT Methods for Python Code Generation

Johanna Männistö, Joseph Attieh and Jörg Tiedemann