Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Akella, Kartheek"'
This work studies the long-standing problems of model capacity and negative interference in multilingual neural machine translation MNMT. We use network pruning techniques and observe that pruning 50-70% of the parameters from a trained MNMT model re
Externí odkaz:
http://arxiv.org/abs/2107.09622
Autor:
Akella, Kartheek, Allu, Sai Himal, Ragupathi, Sridhar Suresh, Singhal, Aman, Khan, Zeeshan, Namboodiri, Vinay P., Jawahar, C V
In this paper, we address the task of improving pair-wise machine translation for specific low resource Indian languages. Multilingual NMT models have demonstrated a reasonable amount of effectiveness on resource-poor languages. In this work, we show
Externí odkaz:
http://arxiv.org/abs/2012.05786