15 citations · 17 across the 4 of their papers we have counts for
4 papers
Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders
Bendegúz Váradi, Zoltán Kmetty
We present a Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoder (SAE) for extracting cross-seed universal features from independently trained BERT models. Cross-seed…
Boosting classification reliability of NLP transformer models in the long run
Zoltán Kmetty, Bence Kollányi, Krisztián Boros
Transformer-based machine learning models have become an essential tool for many natural language processing (NLP) tasks since the introduction of the method. A common objective of…
The presence of occupational structure in online texts based on word embedding NLP models
Zoltán Kmetty, Julia Koltai, Tamás Rudas
Research on social stratification is closely linked to analysing the prestige associated with different occupations. This research focuses on the positions of occupations in the se…
How to measure musical preference on Facebook? Evidence from a mixed-method data collection
Zoltán Kmetty, Renáta Németh
More and more digital data is available for social science analysis. This provides new ways of measuring several concepts. But when we start using new data sources, we have to unde…