4 citations · 5 across the 4 of their papers we have counts for
4 papers
The Token Tax: Systematic Bias in Multilingual Tokenization
Jessica M. Lundin, Ada Zhang, Nihal Karim +4
Tokenization inefficiency imposes structural disadvantages on morphologically complex, low-resource languages, inflating compute resources and depressing accuracy. We evaluate 10 l…
No Text Needed: Forecasting MT Quality and Inequity from Fertility and Metadata
Jessica M. Lundin, Ada Zhang, David Adelani +1
We show that translation quality can be predicted with surprising accuracy \textit{without ever running the translation system itself}. Using only a handful of features, token fert…
Learning delay dynamics for multivariate stochastic processes, with application to the prediction of the growth rate of COVID-19 cases in the United States
Paromita Dubey, Yaqing Chen, Álvaro Gajardo +5
Delay differential equations form the underpinning of many complex dynamical systems. The forward problem of solving random differential equations with delay has received increasin…
Latent Deformation Models for Multivariate Functional Data and Time Warping Separability
Cody Carroll, Hans-Georg Müller
Multivariate functional data present theoretical and practical complications which are not found in univariate functional data. One of these is a situation where the component func…