On the Complementarity between Human Translators and Machine Translation

Maite Aragonés Lumeras,Andy Way

doi:10.7146/hjlcb.v0i56.97200

Abstract

Many translators are fearful of the impact of Machine Translation (MT) on their profession, broadly speaking, and on their livelihoods more specifically. We contend that their concern is misplaced, as human translators have a range of skills, many of which are currently – with no signs of any imminent breakthroughs on the horizon – impossible to replicate by automatic means. Nonetheless, in this paper, we will show that MT engines have considerable potential to improve translators’ productivity and ensure that the output translations are more consistent. Furthermore, we will investigate what machines are good at, where they break down, and why the human is likely to remain the most critical component in the translation pipeline for many years to come.

Highlights

Machine Translation (MT) is being used by many people on a daily basis as a productivity tool, with demonstrable success
Many people are trying to work on incorporating linguistic rules into statistical approaches to MT (SMT) in order to try to go beyond the current performance ceiling, but it is by no means as straightforward as one might think, especially from a human translator’s point of view
Concluding Remarks In this paper, we have attempted to demonstrate the particular strengths and weaknesses of both human translators and MT systems, especially today’s prevalent statistical models. Rather than note this to be problematic, we have shown that it is precisely those areas where humans struggle where SMT systems can help, and in contrast, that where SMT systems go astray, these are cases where human translators are especially efficient

Summary

Introduction

Machine Translation (MT) is being used by many people on a daily basis as a productivity tool, with demonstrable success. Many of these new, emerging use-cases for raw MT and post-edited MT (PEMT) – especially involving user-generated content (UGC) – require different levels of human engagement, and different levels of quality (Penkale/Way 2013).

Results

Conclusion