5 papers
MeVer at CheckThat! 2026: Cluster-Aware Hard-Negative Mining for Multilingual Scientific Source Retrieval
Juli Bakagianni, Symeon Papadopoulos
Identifying the scientific source behind a social media claim requires matching short, informal, and often multilingual claims against large collections of scientific publications,…
TopClustRAG at SIGIR 2025 LiveRAG Challenge
Juli Bakagianni, John Pavlopoulos, Aristidis Likas
We present TopClustRAG, a retrieval-augmented generation (RAG) system developed for the LiveRAG Challenge, which evaluates end-to-end question answering over large-scale web corpor…
A Systematic Survey of Natural Language Processing for the Greek Language
Juli Bakagianni, Kanella Pouli, Maria Gavriilidou +1
Comprehensive monolingual Natural Language Processing (NLP) surveys are essential for assessing language-specific challenges, resource availability, and research gaps. However, exi…
SemEval-2025 Task 9: The Food Hazard Detection Challenge
Korbinian Randl, John Pavlopoulos, Aron Henriksson +2
In this challenge, we explored text-based food hazard prediction with long tail distributed classes. The task was divided into two subtasks: (1) predicting whether a web text impli…
Open or Closed LLM for Lesser-Resourced Languages? Lessons from Greek
John Pavlopoulos, Juli Bakagianni, Kanella Pouli +1
Natural Language Processing (NLP) for lesser-resourced languages faces persistent challenges, including limited datasets, inherited biases from high-resource languages, and the nee…