CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks

TL;DR

This paper describes a neural sequence-to-sequence system designed for WMT 2016 tasks of automatic post-editing and multimodal translation, leveraging recent neural learning techniques to improve machine translation quality.

Contribution

It introduces a neural system that applies recent sequence learning methods to enhance performance on post-editing and multimodal translation tasks.

Findings

Achieved competitive results on WMT 2016 tasks

Utilized neural sequence-to-sequence models effectively

Demonstrated the applicability of recent neural methods in translation tasks

Abstract

Neural sequence to sequence learning recently became a very promising paradigm in machine translation, achieving competitive results with statistical phrase-based systems. In this system description paper, we attempt to utilize several recently published methods used for neural sequential learning in order to build systems for WMT 2016 shared tasks of Automatic Post-Editing and Multimodal Machine Translation.