Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description

TL;DR

This paper reports on the second shared task in multimodal machine translation and multilingual image description, highlighting system improvements and new task setups involving additional languages and test conditions.

Contribution

It introduces new language and test set extensions for multimodal translation and modifies the image description task to test systems with only images at test time.

Findings

Multimodal systems showed improvement over previous year.

Text-only systems remain competitive in the new tasks.

New languages and test conditions were successfully integrated.

Abstract

We present the results from the second shared task on multimodal machine translation and multilingual image description. Nine teams submitted 19 systems to two tasks. The multimodal translation task, in which the source sentence is supplemented by an image, was extended with a new language (French) and two new test sets. The multilingual image description task was changed such that at test time, only the image is given. Compared to last year, multimodal systems improved, but text-only systems remain competitive.