A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
We propose EdgeFormer -- a parameter-efficient Transformer of the encoder-decoder architecture for on-device seq2seq generation, which is customized under strict computation and memory constraints. ... We conduct extensive experiments on two practical on-device seq2seq tasks: Machine Translation and Grammatical Error Correction, and show that EdgeFormer can effectively outperform previous parameter-efficient ... on-device seq2seq generation in real-word applications, and help from Emma Ning, Wenbing Li, Ye Wang and Bowen Bao in the Microsoft ONNX team with onnxruntime. ...arXiv:2202.07959v2 fatcat:m3uugp3tgre7ndbs7ebjjswcu4