Search Results for author: András Lukács

Found 4 papers, 2 papers with code

LlamBERT: Large-scale low-cost data annotation in NLP

1 code implementation23 Mar 2024 Bálint Csanády, Lajos Muzsai, Péter Vedres, Zoltán Nádasdy, András Lukács

Large Language Models (LLMs), such as GPT-4 and Llama 2, show remarkable proficiency in a wide range of natural language processing (NLP) tasks.

 Ranked #1 on Sentiment Analysis on IMDb (using extra training data)

Sentiment Analysis Text Classification

Deep learning the Hurst parameter of linear fractional processes and assessing its reliability

no code implementations3 Jan 2024 Dániel Boros, Bálint Csanády, Iván Ivkovic, Lóránt Nagy, András Lukács, László Márkus

The study concludes that while deep learning methods show promise in parameter estimation of fractional processes, their effectiveness is contingent on the process type and the quality of training data.

Dilated Convolutional Neural Networks for Lightweight Diacritics Restoration

1 code implementation LREC 2022 Bálint Csanády, András Lukács

Our solution surpasses the performance of similarly sized models and is also competitive with larger models.

Cannot find the paper you are looking for? You can Submit a new open access paper.