Issue #99 – Training Neural Machine Translation with Semantic Similarity
17 Sep20
Issue #99 – Training Neural Machine Translation with Semantic Similarity
Author: Dr. Karin Sim, Machine Translation Scientist @ Iconic
Introduction
The standard way of training Neural Machine Translation (NMT) systems is by Maximum Likelihood Estimation (MLE), and although there have been experiments in the past to optimize systems directly in order to improve particular evaluation metrics, these were of limited success. Of course, using BLEU is not ideal due to the fact that it fails to account for semantic similarity, penalises similar hypothesis which differ lexically, and doesn’t assign partial credit. Attempts at training to directly maximize semantic metrics have been more successful, albeit for Statistical Machine Translation (SMT): both Lo et al (2013) and Beloucif et al (2014) maximised the semantic frame based metric MEANT (Lo et al. (2012)) in tuning, which resulted in improvements as measured by human judgements. This is exciting as it slowly inches closer to the way a human translator would evaluate some aspects of a translation.
In today’s blog we investigate some new work by Wieting et al (2019) to incorporate semantic similarity into the