papers

Publications (6)

cs.SI2024

Commute-Time-Optimised Graphs for GNNs

Igor Sterner, Shiye Su, Petar Veličković

We explore graph rewiring methods that optimise commute time. Recent graph rewiring approaches facilitate long-range interactions in sparse graphs, making such rewirings commute-ti…

cs.CL2026

Contrastive Learning with Narrative Twins for Modeling Story Salience

Igor Sterner, Alex Lascarides, Frank Keller

Understanding narratives requires identifying which events are most salient for a story's progression. We present a contrastive learning framework for modeling narrative salience t…

cs.CL2025

Minimal Pair-Based Evaluation of Code-Switching

Igor Sterner, Simone Teufel

There is a lack of an evaluation methodology that estimates the extent to which large language models (LLMs) use code-switching (CS) in the same way as bilinguals. Existing methods…

cs.CL2025

Code-Switching and Syntax: A Large-Scale Experiment

Igor Sterner, Simone Teufel

The theoretical code-switching (CS) literature provides numerous pointwise investigations that aim to explain patterns in CS, i.e. why bilinguals switch language in certain positio…

cs.CL2024

Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches

Igor Sterner, Weizhe Lin, Jinghong Chen +1

Two approaches have emerged to input images into large language models (LLMs). The first is to caption images into natural language. The second is to map image feature embeddings i…

cs.CL2024

Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation

Markus Frohmann, Igor Sterner, Ivan Vulić +2

Segmenting text into sentences plays an early and crucial role in many NLP systems. This is commonly achieved by using rule-based or statistical methods relying on lexical features…