Zobrazeno 1 - 10
of 2 512
pro vyhledávání: '"Atanasova, P."'
Autor:
Marjanović, Sara Vera, Yu, Haeun, Atanasova, Pepa, Maistro, Maria, Lioma, Christina, Augenstein, Isabelle
Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge. Nevertheless, studies indicate that LMs often ignore the pro
Externí odkaz:
http://arxiv.org/abs/2407.17023
Explaining the decision-making process of machine learning models is crucial for ensuring their reliability and fairness. One popular explanation form highlights key input features, such as i) tokens (e.g., Shapley Values and Integrated Gradients), i
Externí odkaz:
http://arxiv.org/abs/2406.15085
Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and further for upd
Externí odkaz:
http://arxiv.org/abs/2404.18655
This paper is a short overview of the main Abelian- and Tauberian-type results from [4, 14, 26] regarding the asymptotic analysis of different classes of generalized functions in terms of appropriate frames. The Tauberian-type results provide a compr
Externí odkaz:
http://arxiv.org/abs/2404.04468
Describing the ground states of continuous, real-space quantum many-body systems, like atoms and molecules, is a significant computational challenge with applications throughout the physical sciences. Recent progress was made by variational methods b
Externí odkaz:
http://arxiv.org/abs/2402.06577
We study bulk particle transport in a Fermi-Hubbard model on an infinite-dimensional Bethe lattice, driven by a constant electric field. Previous numerical studies showed that one dimensional analogs of this system exhibit a breakdown of diffusion du
Externí odkaz:
http://arxiv.org/abs/2311.08893
Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehension (MRC) or natural language inference (NLI). However, existing highli
Externí odkaz:
http://arxiv.org/abs/2310.13506
Autor:
Gregor Petrič, Sara Atanasova
Publikováno v:
BMC Public Health, Vol 24, Iss 1, Pp 1-11 (2024)
Abstract Background Given the rapid proliferation and use of online health resources, many of which may be of dubious quality, there is an increasing need to develop electronic health literacy (e-health literacy) skills among the population of intern
Externí odkaz:
https://doaj.org/article/34531de4d31b47448351175fe7cdb504
Autor:
Ana Marković, Mariyana Atanasova, Rossen Buyukliev, Adriana Bakalova, Andrija Šmelcerović, Emiliya Cherneva
Publikováno v:
Pharmacia, Vol 71, Iss , Pp 1-7 (2024)
Deoxyribonuclease I (DNase I) is one of the main nucleases involved in deoxyribonucleic acid (DNA) degradation during apoptosis. It catalyzes the hydrolytic cleavage of DNA, producing 5‘-oligonucleotides. The inhibition of DNase I may serve as an i
Externí odkaz:
https://doaj.org/article/9d84c0a8d3be4775ba71cf48fe2c1e67
Autor:
Hardalov, Momchil, Atanasova, Pepa, Mihaylov, Todor, Angelova, Galia, Simov, Kiril, Osenova, Petya, Stoyanov, Ves, Koychev, Ivan, Nakov, Preslav, Radev, Dragomir
Publikováno v:
ACL 2023
We present bgGLUE(Bulgarian General Language Understanding Evaluation), a benchmark for evaluating language models on Natural Language Understanding (NLU) tasks in Bulgarian. Our benchmark includes NLU tasks targeting a variety of NLP problems (e.g.,
Externí odkaz:
http://arxiv.org/abs/2306.02349