Zobrazeno 1 - 10
of 429
pro vyhledávání: '"JAUREGI, P."'
Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial examples is to
Externí odkaz:
http://arxiv.org/abs/2405.11904
Cross-lingual summarization (XLS) generates summaries in a language different from that of the input documents (e.g., English to Spanish), allowing speakers of the target language to gain a concise view of their content. In the present day, the predo
Externí odkaz:
http://arxiv.org/abs/2403.13240
Cross-lingual text classification leverages text classifiers trained in a high-resource language to perform text classification in other languages with no or minimal fine-tuning (zero/few-shots cross-lingual transfer). Nowadays, cross-lingual text cl
Externí odkaz:
http://arxiv.org/abs/2306.04996
Autor:
Iván de la Hera, Fernando Alda, Lourdes Ancin, Emilio Barba, Joseba Butroe Jauregi, Alberto Castro, Aitor Cevidanes, David Galicia, Alberto Gosá, Arturo Elosegi, Cristina Herrero-Jáuregui, Asier Hilario, Ricardo Ibáñez, Eduardo Leorri, Beatriz Martín, Ibai Olariaga, María Torres-Sánchez, Brian Webster
Publikováno v:
Munibe Ciencias Naturales, Vol 72 (2024)
Se cumple el 75 aniversario (1949-2024) del lanzamiento del primer volumen de la revista Munibe por parte de los fundadores de la Sociedad de Ciencias Aranzadi. Aprovechando la celebración de esta efeméride, en este trabajo se hace un breve repaso
Externí odkaz:
https://doaj.org/article/07b8dac6f64f4e158eb0a57b52b5088f
Multi-document summarization (MDS) has made significant progress in recent years, in part facilitated by the availability of new, dedicated datasets and capacious language models. However, a standing limitation of these models is that they are traine
Externí odkaz:
http://arxiv.org/abs/2203.02894
Autor:
David Cantero Burgos, Ekaitz Jauregi Iztueta, Inaki Maurtua Ormaechea, Jose Maria Martinez-Otzeta, Andrea Cabrera Mugica
Publikováno v:
IEEE Access, Vol 12, Pp 127862-127878 (2024)
Automotive Driver Assistance Systems (ADAS) applications are currently an intensive field of study and innovation. The development of an ADAS is a multidisciplinary task involving electronic hardware design, advanced software implementation, safety c
Externí odkaz:
https://doaj.org/article/178613e56fb94747acea2342f416ba30
To date, most abstractive summarisation models have relied on variants of the negative log-likelihood (NLL) as their training objective. In some cases, reinforcement learning has been added to train the models with an objective that is closer to thei
Externí odkaz:
http://arxiv.org/abs/2106.04080
Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on the recentl
Externí odkaz:
http://arxiv.org/abs/2106.02208
Publikováno v:
PeerJ Analytical Chemistry, Vol 6, p e32 (2024)
Natural deep eutectic solvents (NADES) have emerged as an eco-friendly alternative for extracting bioactives, avoiding the use of flammable organic solvents and extreme temperatures and pH conditions. NADES rely on intermolecular interactions between
Externí odkaz:
https://doaj.org/article/894a54e4fbcf4dd2ab0a146cb5d60849
Document-level machine translation focuses on the translation of entire documents from a source to a target language. It is widely regarded as a challenging task since the translation of the individual sentences in the document needs to retain aspect
Externí odkaz:
http://arxiv.org/abs/2010.03732