4 papers · 1 filter
Supervised In-Context Fine-Tuning for Generative Sequence Labeling
David Dukić, Goran Glavaš, Jan Šnajder
Sequence labeling (SL) tasks, where labels are assigned to tokens, are abundant in NLP (e.g., named entity recognition and aspect-based sentiment analysis). Owing to the intuition…
TakeLab Retriever: AI-Driven Search Engine for Articles from Croatian News Outlets
David Dukić, Marin Petričević, Sven Ćurković +1
TakeLab Retriever is an AI-driven search engine designed to discover, collect, and semantically analyze news articles from Croatian news outlets. It offers a unique perspective on…
Are ELECTRA's Sentence Embeddings Beyond Repair? The Case of Semantic Textual Similarity
Ivan Rep, David Dukić, Jan Šnajder
While BERT produces high-quality sentence embeddings, its pre-training computational cost is a significant drawback. In contrast, ELECTRA provides a cost-effective pre-training obj…
Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling
David Dukić, Jan Šnajder
Pre-trained language models based on masked language modeling (MLM) excel in natural language understanding (NLU) tasks. While fine-tuned MLM-based encoders consistently outperform…