Zobrazeno 1 - 10
of 1 741
pro vyhledávání: '"A, Marneffe"'
Autor:
Bogaert, Jeremie, de Marneffe, Marie-Catherine, Descampe, Antonin, Escouflaire, Louis, Fairon, Cedrick, Standaert, Francois-Xavier
Publikováno v:
Traitement Automatique des Langues 64, 2023, ATALA, Paris
Large language models (LLMs) perform very well in several natural language processing tasks but raise explainability challenges. In this paper, we examine the effect of random elements in the training of LLMs on the explainability of their prediction
Externí odkaz:
http://arxiv.org/abs/2410.05085
Human label variation arises when annotators assign different labels to the same item for valid reasons, while annotation errors occur when labels are assigned for invalid reasons. These two issues are prevalent in NLP benchmarks, yet existing resear
Externí odkaz:
http://arxiv.org/abs/2403.01931
Human label variation, or annotation disagreement, exists in many natural language processing (NLP) tasks, including natural language inference (NLI). To gain direct evidence of how NLI label variation arises, we build LiveNLI, an English dataset of
Externí odkaz:
http://arxiv.org/abs/2310.13850
Understanding and Predicting Human Label Variation in Natural Language Inference through Explanation
Human label variation (Plank 2022), or annotation disagreement, exists in many natural language processing (NLP) tasks. To be robust and trusted, NLP models need to identify such variation and be able to explain it. To this end, we created the first
Externí odkaz:
http://arxiv.org/abs/2304.12443
Autor:
Mira Meeus, Wim Marneffe, Julie Sylvie van Eetvelde, Annick A A Timmermans, Karin Coninx, Kristof Kempeneers, Timo Meus, Iris Meuwissen, Nathalie Anne Roussel, Gaetane Stassijns, Jonas Verbrugghe
Publikováno v:
BMJ Open Sport & Exercise Medicine, Vol 10, Iss 4 (2024)
Chronic low back pain (CLBP) is one of the most common chronic musculoskeletal disorders worldwide. Guidelines recommend exercise therapy (ET) in CLBP management, but more research is needed to investigate specific ET modalities and their underlying
Externí odkaz:
https://doaj.org/article/52256d9de9224860988285eefb226969
Autor:
Sarah Misplon, Wim Marneffe, Jana Missiaen, Dries Myny, Inge Decock, Steve Lervant, Koen Vaneygen
Publikováno v:
Archives of Public Health, Vol 82, Iss 1, Pp 1-11 (2024)
Abstract Background Oncological home hospitalization (HH) was implemented in a Belgian context to evaluate the feasibility of oncological HH. In a first HH model (HH1), implemented by three Belgian hospitals, two home nursing organizations and a grou
Externí odkaz:
https://doaj.org/article/ebd0edf8c15a4760b07433e6af3f3b56
We investigate how disagreement in natural language inference (NLI) annotation arises. We developed a taxonomy of disagreement sources with 10 categories spanning 3 high-level classes. We found that some disagreements are due to uncertainty in the se
Externí odkaz:
http://arxiv.org/abs/2209.03392
Autor:
P.-J. Wyndaele, J.-F. de Marneffe, S. Sergeant, C. J. L. de la Rosa, S. Brems, A. M. Caro, S. De Gendt
Publikováno v:
npj 2D Materials and Applications, Vol 8, Iss 1, Pp 1-11 (2024)
Abstract The full utilization of two-dimensional transition metal dichalcogenides (2D TMDCs) faces several challenges, among which is realizing uniform material deposition on the 2D surface. Typical strategies to enable material growth lead to a poor
Externí odkaz:
https://doaj.org/article/ccc03cc112f3408c89471794b1980979
Autor:
Araks Martirosyan, Rizwan Ansari, Francisco Pestana, Katja Hebestreit, Hayk Gasparyan, Razmik Aleksanyan, Silvia Hnatova, Suresh Poovathingal, Catherine Marneffe, Dietmar R. Thal, Andrew Kottick, Victor J. Hanson-Smith, Sebastian Guelfi, William Plumbly, T. Grant Belgard, Emmanouil Metzakopian, Matthew G. Holt
Publikováno v:
Molecular Neurodegeneration, Vol 19, Iss 1, Pp 1-24 (2024)
Abstract Parkinson’s Disease (PD) is the second most common neurodegenerative disorder. The pathological hallmark of PD is loss of dopaminergic neurons and the presence of aggregated α-synuclein, primarily in the substantia nigra pars compacta (SN
Externí odkaz:
https://doaj.org/article/ac5a812e7fc64915b2e68e33cecdd4a4
We investigate how well BERT performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions. Although BERT obtains a strong performance on most datasets, it does so by exploiting common surface p
Externí odkaz:
http://arxiv.org/abs/2107.00807