![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in Translation
![]() You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in TranslationAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact nobody. RCL - Representing, calibrating & leveraging prediction uncertainty from statistics to machine learning The goal of translation, be it by human or by machine, is, given some textin a source language, to produce text in a target language that simultaneously 1) preserves the meaning of the source text and 2) achieves natural expression in the target language. However, researchers in the machine translation community usually assess translations using a single score in-tended to capture semantic accuracy and the naturalness of the output simultaneously. In this talk, I build on Michaeli and Blau’s the seminal work on distortion-perception theory to propose a general notion of accuracy and naturalness, and show that such single-score summaries do not and cannot give the complete picture of a translation system’s true performance. I also demonstrate the accuracy-naturalness tradeoff by evaluating the performance of the state-of-the-art translation systems on a popular benchmark. These findings help explain well-known empirical phenomena, such as the observation that optimizing translation systems for a specific accuracy metric initially improves the system’s naturalness, while “overfitting” the system to the metric can significantly degrade its naturalness. Finally, I propose a new statistical distance in the spirit of integral probability metrics to measure naturalness in practice and discuss some of its properties. This talk is part of the Isaac Newton Institute Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsDarwin College Erasmus Seminar Series J Africa Together Conference 2022Other talksNamibia: Etosha National Park & Lithops Generative AI and Diffusion Models: a Statistical Physics Analysis External Seminar - Magdalena Bezanilla TBC Scalable sequential design for Bayesian inverse problems via conditional transport Physics informed Gaussian process priors Topological order in Chiral Liquid Crystals |