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.

本研究探讨了预训练词嵌入及其在多模式神经机器翻译模型中的应用，引入两种去偏差技术，并在英德翻译和英法翻译两种语言对上获得了最多 + 1.93 BLEU 和 + 2.02 METEOR 的性能提升。

消除词嵌入中的偏见改善多模式机器翻译

Debiasing Word Embeddings Improves Multimodal Machine Translation

In this paper we describe the use of text classification methods to
investigate genre and method variation in an English - German translation
corpus. For this purpose we use linguistically motivated features representing
texts using a combination of part-of-speech tags arranged in bigrams, trigrams,
and 4-grams. The classification method used in this paper is a Bayesian
classifier with Laplace smoothing. We use the output of the classifiers to
carry out an extensive feature analysis on the main difference between genres
and methods of translation.

本文利用文本分类方法研究英德翻译语料库的类型和方法变化，使用基于词性标注的特征的组合，包括二元组、三元组和四元组，采用拉普拉斯平滑的贝叶斯分类器。使用分类器的输出对不同类型和翻译方法的主要区别进行了广泛的特征分析。