SOTAVerified

Character Mapping and Ad-hoc Adaptation: Edinburgh's IWSLT 2020 Open Domain Translation System

2020-07-01WS 2020Unverified0· sign in to hype

Pin-zhen Chen, Nikolay Bogoychev, Ulrich Germann

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

This paper describes the University of Edinburgh's neural machine translation systems submitted to the IWSLT 2020 open domain JapaneseChinese translation task. On top of commonplace techniques like tokenisation and corpus cleaning, we explore character mapping and unsupervised decoding-time adaptation. Our techniques focus on leveraging the provided data, and we show the positive impact of each technique through the gradual improvement of BLEU.

Tasks

Reproductions