2 papers
cs.LG2023
Dynamic Stashing Quantization for Efficient Transformer Training
Guo Yang, Daniel Lo, Robert Mullins +1
Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks. Unfortunately, the immense amount of computations and m…
cs.CL2019
Two-stage Training for Chinese Dialect Recognition
Zongze Ren, Guofu Yang, Shugong Xu
In this paper, we present a two-stage language identification (LID) system based on a shallow ResNet14 followed by a simple 2-layer recurrent neural network (RNN) architecture, whi…