Debiasing Word Embeddings Improves Multimodal Machine Translation
This addresses a specific bottleneck in multimodal NMT for researchers and practitioners, but it is incremental as it applies known debiasing methods to a new task.
The study tackled the hubness problem in pretrained word embeddings for multimodal neural machine translation by introducing two debiasing techniques, improving performance by up to +1.93 BLEU and +2.02 METEOR for English-German and +1.73 BLEU and +0.95 METEOR for English-French translation.
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.