no code implementations • 20 Feb 2024 • Ivan Rep, David Dukić, Jan Šnajder
While BERT produces high-quality sentence embeddings, its pre-training computational cost is a significant drawback.
no code implementations • 25 Jan 2024 • David Dukić, Jan Šnajder
While fine-tuned MLM-based encoders consistently outperform causal language modeling decoders of comparable size, recent decoder-only large language models (LLMs) perform on par with smaller MLM-based encoders.
1 code implementation • 23 May 2023 • David Dukić, Kiril Gashteovski, Goran Glavaš, Jan Šnajder
We address the problem of negative transfer in TD by coupling triggers between domains using subject-object relations obtained from a rule-based open information extraction (OIE) system.