no code implementations • 12 Mar 2024 • Robert Lakatos, Peter Pollner, Andras Hajdu, Tamas Joo
Furthermore, we outline a simple RAG-based architecture which, on average, outperforms the FN models by 16% in terms of the ROGUE score, 15% in the case of the BLEU score, and 53% based on the cosine similarity.
no code implementations • 19 Sep 2023 • Robert Lakatos, Peter Pollner, Andras Hajdu, Tamas Joo
Introduction: Covert tobacco advertisements often raise regulatory measures.
no code implementations • 13 Jun 2023 • Robert Lakatos, Gergo Bogacsovics, Balazs Harangi, Istvan Lakatos, Attila Tiba, Janos Toth, Marianna Szabo, Andras Hajdu
The efficiency of natural language processing has improved dramatically with the advent of machine learning models, particularly neural network-based solutions.