Prati
Nathan Hoyen Ng
Nathan Hoyen Ng
Potvrđena adresa e-pošte na cs.toronto.edu - Početna stranica
Naslov
Citirano
Citirano
Godina
fairseq: A fast, extensible toolkit for sequence modeling
M Ott, S Edunov, A Baevski, A Fan, S Gross, N Ng, D Grangier, M Auli
arXiv preprint arXiv:1904.01038, 2019
19992019
Facebook FAIR's WMT19 news translation task submission
N Ng, K Yee, A Baevski, M Ott, M Auli, S Edunov
arXiv preprint arXiv:1907.06616, 2019
2752019
SSMBA: Self-supervised manifold based data augmentation for improving out-of-domain robustness
N Ng, K Cho, M Ghassemi
arXiv preprint arXiv:2009.10195, 2020
592020
Simple and effective noisy channel modeling for neural machine translation
K Yee, N Ng, YN Dauphin, M Auli
arXiv preprint arXiv:1908.05731, 2019
572019
Predicting surgery duration with neural heteroscedastic regression
NH Ng, RA Gabriel, J McAuley, C Elkan, ZC Lipton
Machine Learning for Healthcare Conference, 100-111, 2017
242017
Embryo staging with weakly-supervised region selection and dynamically-decoded predictions
T Lau, N Ng, J Gingold, N Desai, J McAuley, ZC Lipton
Machine Learning for Healthcare Conference, 663-679, 2019
21*2019
Improving dialogue breakdown detection with semi-supervised learning
N Ng, M Ghassemi, N Thangarajan, J Pan, Q Guo
arXiv preprint arXiv:2011.00136, 2020
62020
If Influence Functions are the Answer, Then What is the Question?
J Bae, N Ng, A Lo, M Ghassemi, R Grosse
arXiv preprint arXiv:2209.05364, 2022
32022
Predicting out-of-domain generalization with local manifold smoothness
N Ng, K Cho, N Hulkund, M Ghassemi
arXiv preprint arXiv:2207.02093, 2022
22022
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–9