3 papers
cs.CL2024
BEIR-NL: Zero-shot Information Retrieval Benchmark for the Dutch Language
Nikolay Banar, Ehsan Lotfi, Walter Daelemans
Zero-shot evaluation of information retrieval (IR) models is often performed using BEIR; a large and heterogeneous benchmark composed of multiple datasets, covering different retri…
cs.CL2024
Bilingual BSARD: Extending Statutory Article Retrieval to Dutch
Ehsan Lotfi, Nikolay Banar, Nerses Yuzbashyan +1
Statutory article retrieval plays a crucial role in making legal information more accessible to both laypeople and legal professionals. Multilingual countries like Belgium present…
cs.CL2024
PersonalityChat: Conversation Distillation for Personalized Dialog Modeling with Facts and Traits
Ehsan Lotfi, Maxime De Bruyn, Jeska Buhmann +1
The new wave of Large Language Models (LLM) has offered an efficient tool to curate sizeable conversational datasets. So far studies have mainly focused on task-oriented or generic…