Yang Yu

TL;DR: The authors proposed a tuplemax loss to model prior knowledge for language identification, which achieved a 2.33% error rate, which is a relative 39.4% improvement over the standard softmax loss method.

TL;DR: This work replaces the commonly used softmax loss function with a novel loss function named tuplemax loss, which achieves a 2.33% error rate, which is a relative 39.4% improvement over the 3.85%error rate of standard soft max loss method.

TL;DR: Experimental results show that the deep neural network model outperforms the lattice-based ensemble model, and it reduced the error rate from 5.5% in the baseline to 4.3%, which is a 21.8% relative reduction.

TL;DR: A prompt-based vision-aware language modeling (PVLM) approach to MSA, which only requires a few supervised data and can incorporate the visual information into pre-trained language model and leverage prompt tuning to bridge the gap between masked language prediction in pre-training and MSA tasks.