Zobrazeno 1 - 10
of 284
pro vyhledávání: '"Šnajder, Jan"'
Autor:
Majer, Laura, Šnajder, Jan
The increasing threat of disinformation calls for automating parts of the fact-checking pipeline. Identifying text segments requiring fact-checking is known as claim detection (CD) and claim check-worthiness detection (CW), the latter incorporating c
Externí odkaz:
http://arxiv.org/abs/2404.12174
Autor:
Jukić, Josip, Šnajder, Jan
Enhancing generalization and uncertainty quantification in pre-trained language models (PLMs) is crucial for their effectiveness and reliability. Building on machine learning research that established the importance of robustness for improving genera
Externí odkaz:
http://arxiv.org/abs/2404.00758
News headlines often evoke sentiment by intentionally portraying entities in particular ways, making targeted sentiment analysis (TSA) of headlines a worthwhile but difficult task. Due to its subjectivity, creating TSA datasets can involve various an
Externí odkaz:
http://arxiv.org/abs/2403.00418
While BERT produces high-quality sentence embeddings, its pre-training computational cost is a significant drawback. In contrast, ELECTRA delivers a cost-effective pre-training objective and downstream task performance improvements, but not as perfor
Externí odkaz:
http://arxiv.org/abs/2402.13130
Autor:
Dukić, David, Šnajder, Jan
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 causal language modeling decoders of comparable size, recent decoder-
Externí odkaz:
http://arxiv.org/abs/2401.14556
Effective out-of-distribution (OOD) detection is crucial for reliable machine learning models, yet most current methods are limited in practical use due to requirements like access to training data or intervention in training. We present a novel meth
Externí odkaz:
http://arxiv.org/abs/2310.02832
Autor:
Jukić, Josip, Šnajder, Jan
Pre-trained language models (PLMs) have ignited a surge in demand for effective fine-tuning techniques, particularly in low-resource domains and languages. Active learning (AL), a set of algorithms designed to decrease labeling costs by minimizing la
Externí odkaz:
http://arxiv.org/abs/2305.14576
Event detection is a crucial information extraction task in many domains, such as Wikipedia or news. The task typically relies on trigger detection (TD) -- identifying token spans in the text that evoke specific events. While the notion of triggers s
Externí odkaz:
http://arxiv.org/abs/2305.14163
Autor:
Medić, Zoran, Šnajder, Jan
Citation recommendation (CR) models may help authors find relevant articles at various stages of the paper writing process. Most research has dealt with either global CR, which produces general recommendations suitable for the initial writing stage,
Externí odkaz:
http://arxiv.org/abs/2305.12190
Active learning (AL) aims to reduce labeling costs by querying the examples most beneficial for model learning. While the effectiveness of AL for fine-tuning transformer-based pre-trained language models (PLMs) has been demonstrated, it is less clear
Externí odkaz:
http://arxiv.org/abs/2305.09807