Zobrazeno 1 - 10
of 1 304
pro vyhledávání: '"Martínez, Felipe"'
Crawling parallel texts $\unicode{x2014}$texts that are mutual translations$\unicode{x2014}$ from the Internet is usually done following a brute-force approach: documents are massively downloaded in an unguided process, and only a fraction of them en
Externí odkaz:
http://arxiv.org/abs/2405.14779
Autor:
Tian, Yuchen, Moreno, Ari R. Ortiz, Chipaux, Mayeul, Wu, Kaiqi, Martinez, Felipe P. Perona, Shirzad, Hoda, Hamoh, Thamir, Mzyk, Aldona, van Rijn, Patrick, Schirhagl, Romana
Diamond is increasingly popular because of its unique material properties. Diamond defects called nitrogen vacancy (NV) centers allow measurements with unprecedented sensitivity. However, to achieve ideal sensing performance NV centers need to be wit
Externí odkaz:
http://arxiv.org/abs/2404.11961
Autor:
Lou, Andrés, Pérez-Ortiz, Juan Antonio, Sánchez-Martínez, Felipe, Sánchez-Cartagena, Víctor M.
Publikováno v:
2024.naacl-long.156
The Mayan languages comprise a language family with an ancient history, millions of speakers, and immense cultural value, that, nevertheless, remains severely underrepresented in terms of resources and global exposure. In this paper we develop, curat
Externí odkaz:
http://arxiv.org/abs/2404.07673
Autor:
Sánchez-Cartagena, Víctor M., Esplà-Gomis, Miquel, Pérez-Ortiz, Juan Antonio, Sánchez-Martínez, Felipe
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 46, Issue: 2, February 2024)
When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic parallel senten
Externí odkaz:
http://arxiv.org/abs/2401.16086
This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two a
Externí odkaz:
http://arxiv.org/abs/2401.16078
Finding groups of similar image blocks within an ample search area is often necessary in different applications, such as video compression, image clustering, vector quantization, and nonlocal noise reduction. A block-matching algorithm that uses a di
Externí odkaz:
http://arxiv.org/abs/2309.15792
Autor:
Vedelaar, Thea A., Hamoh, Thamir H., Martinez, Felipe Perona, Chipaux, Mayeul, Schirhagl, Romana
The nitrogen-vacancy (NV) center in diamond is a powerful and versatile quantum sensor for diverse quantities. In particular, relaxometry (or T1), allows to detect magnetic noise at the nanoscale. While increasing the number of NV centers in a nanodi
Externí odkaz:
http://arxiv.org/abs/2211.07269
Autor:
Sánchez-Cartagena, Víctor M., Esplà-Gomis, Miquel, Pérez-Ortiz, Juan Antonio, Sánchez-Martínez, Felipe
In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the empirical data
Externí odkaz:
http://arxiv.org/abs/2109.03645
Autor:
Martínez, Felipe1,2,3 (AUTHOR) ctaramasco2@gmail.com, Taramasco, Carla1,4 (AUTHOR) manuel.espinoza@uc.cl, Espinoza, Manuel1,5,6 (AUTHOR) johannaacevedo@udd.cl, Acevedo, Johanna1,7 (AUTHOR) cgoicb@uc.cl, Goic, Carolina1,8,9 (AUTHOR) bnervi@uc.cl, Nervi, Bruno1,10 (AUTHOR)
Publikováno v:
Diagnostics (2075-4418). Mar2024, Vol. 14 Issue 6, p619. 12p.
Autor:
Kondo, Toru, Mogensen, Ulrik M., Talebi, Atefeh, Gasparyan, Samvel B., Campbell, Ross T., Docherty, Kieran F., de Boer, Rudolf A., Inzucchi, Silvio E., Køber, Lars, Kosiborod, Mikhail N., Martinez, Felipe A., Sabatine, Marc S., Bengtsson, Olof, Sjöstrand, Mikaela, Vaduganathan, Muthiah, Solomon, Scott D., Jhund, Pardeep S., McMurray, John J.V.
Publikováno v:
In Journal of the American College of Cardiology 21 May 2024 83(20):1973-1986