papers AI Learner
The Github is limit! Click to go to the new site.

Debiasing Word Embeddings Improves Multimodal Machine Translation

2019-05-28
Tosho Hirasawa, Mamoru Komachi

Abstract

In recent years, pretrained word embeddings have proved useful for multimodal neural machine translation (NMT) models to address the shortage of available datasets. However, the integration of pretrained word embeddings has not yet been explored extensively. Further, pretrained word embeddings in high dimensional spaces have been reported to suffer from the hubness problem. Although some debiasing techniques have been proposed to address this problem for other natural language processing tasks, they have seldom been studied for multimodal NMT models. In this study, we examine various kinds of word embeddings and introduce two debiasing techniques for three multimodal NMT models and two language pairs – English-German translation and English-French translation. With our optimal settings, the overall performance of multimodal models was improved by up to +1.93 BLEU and +2.02 METEOR for English-German translation and +1.73 BLEU and +0.95 METEOR for English-French translation.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.10464

PDF

https://arxiv.org/pdf/1905.10464


Comments

Content