Paper Info
Title
Efficiency through Auto-Sizing - Notre Dame NLP's Submission to the WNGT 2019 Efficiency Task.
Abstract
This paper describes the Notre Dame Natural Language Processing Group's (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 model's parameters while suffering a decrease of only 1.1 BLEU.
Year
DOI
Venue
2019
10.18653/v1/D19-5634
NGT@EMNLP-IJCNLP
DocType
Volume
Citations 
Conference
D19-56
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Kenton Murray100.34
Brian DuSell200.34
David Chiang32843144.76