Efficiency through Auto-Sizing: Notre Dame NLPs Submission to the WNGT 2019 Efficiency Task


Abstract in English

This paper describes the Notre Dame Natural Language Processing Groups (NDNLP) submission to the WNGT 2019 shared task (Hayashi et al., 2019). We investigated the impact of auto-sizing (Murray and Chiang, 2015; Murray et al., 2019) to the Transformer network (Vaswani et al., 2017) with the goal of substantially reducing the number of parameters in the model. Our method was able to eliminate more than 25% of the models parameters while suffering a decrease of only 1.1 BLEU.

Download