Efficient Inference For Neural Machine Translation

Yi-Te Hsu, Sarthak Garg, Yi-Hsiu Liao, Ilya Chatsviorkin

SustaiNLP: Workshop on Simple and Efficient Natural Language Processing Workshop Paper

You can open the pre-recorded video in a separate window.

Abstract: Large Transformer models have achieved state-of-the-art results in neural machine translation and have become standard in the field. In this work, we look for the optimal combination of known techniques to optimize inference speed without sacrificing translation quality. We conduct an empirical study that stacks various approaches and demonstrates that combination of replacing decoder self-attention with simplified recurrent units, adopting a deep encoder and a shallow decoder architecture and multi-head attention pruning can achieve up to 109% and 84% speedup on CPU and GPU respectively and reduce the number of parameters by 25% while maintaining the same translation quality in terms of BLEU.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.