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

Lessons learned in multilingual grounded language learning

2018-09-20
Ákos Kádár, Desmond Elliott, Marc-Alexandre Côté, Grzegorz Chrupała, Afra Alishahi

Abstract

Recent work has shown how to learn better visual-semantic embeddings by leveraging image descriptions in more than one language. Here, we investigate in detail which conditions affect the performance of this type of grounded language learning model. We show that multilingual training improves over bilingual training, and that low-resource languages benefit from training with higher-resource languages. We demonstrate that a multilingual model can be trained equally well on either translations or comparable sentence pairs, and that annotating the same set of images in multiple language enables further improvements via an additional caption-caption ranking objective.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1809.07615

PDF

https://arxiv.org/pdf/1809.07615


Similar Posts

Comments