Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Felice, Mariano"'
Autor:
Zampieri, Marcos, North, Kai, Jauhiainen, Tommi, Felice, Mariano, Kumari, Neha, Nair, Nishant, Bangera, Yash
Language identification is an important first step in many IR and NLP applications. Most publicly available language identification datasets, however, are compiled under the assumption that the gold label of each instance is determined by where texts
Externí odkaz:
http://arxiv.org/abs/2303.01490
This paper presents the first multi-objective transformer model for constructing open cloze tests that exploits generation and discrimination capabilities to improve performance. Our model is further enhanced by tweaking its loss function and applyin
Externí odkaz:
http://arxiv.org/abs/2204.07237
Shortage of available training data is holding back progress in the area of automated error detection. This paper investigates two alternative methods for artificially generating writing errors, in order to create additional resources. We propose tre
Externí odkaz:
http://arxiv.org/abs/1707.05236
Autor:
Felice, Mariano, Specia, Lucia
Publikováno v:
Machine Translation, 2013 Dec 01. 27(3/4), 193-212.
Externí odkaz:
https://www.jstor.org/stable/42628815
