2 code implementations • Findings of the Association for Computational Linguistics 2020 • Isabelle G. Lee, Vera Zu, Sai Srujana Buddi, Dennis Liang, Jack G. M. FitzGerald
CopyNet was the most natural, with a relative perplexity of 1. 59.
Ranked #1 on Machine Translation on Alexa Point of View
1 code implementation • 2 Oct 2020 • Jack G. M. FitzGerald
When no translation is performed, mBART's performance is comparable to the current state of the art system (Cross-Lingual BERT by Xu et al. (2020)) for the languages tested, with better average intent classification accuracy (96. 07% versus 95. 50%) but worse average slot F1 (89. 87% versus 90. 81%).