Odjel za matematiku

Tomislav Prusina

 

PhD student
Department of Mathematics
Josip Juraj Strossmayer University of Osijek
Trg Ljudevita Gaja 6
Osijek, HR-31000, Croatia¸
email: Ova e-mail adresa je zaštićena od spambota. Potrebno je omogućiti JavaScript da je vidite.
office: 8 (ground floor)

 


Research Interests

Machine learning

Degrees

MSc in mathematics, Mathematics and Computer Science, Department of Mathematics, University of Osijek, Croatia, 2022.
BSc in Computer Science, Department of Mathematics, University of Osijek, Croatia, 2020.

 


 

Publications

Technical Reports

  1. T. Prusina, D. Matijević, L. Borozan, J. Maltar, A. Jovanović, Compressing Sentence Representation with maximum Coding Rate Reduction (2023)
    In most natural language inference problems, sentence representation is needed for semantic retrieval tasks. In recent years, pre-trained large language models have been quite effective for computing such representations. These models produce high-dimensional sentence embeddings. An evident performance gap between large and small models exists in practice. Hence, due to space and time hardware limitations, there is a need to attain comparable results when using the smaller model, which is usually a distilled version of the large language model. In this paper, we assess the model distillation of the sentence representation model Sentence-BERT by augmenting the pre-trained distilled model with a projection layer additionally learned on the Maximum Coding Rate Reduction (MCR2)objective, a novel approach developed for general-purpose manifold clustering. We demonstrate that the new language model with reduced complexity and sentence embedding size can achieve comparable results on semantic retrieval benchmarks.



Teaching

Konzultacije (Office Hours): Konzultacije su moguće i po dogovoru.

 


 

Personal

Birthplace: Osijek.