Search

Unsupervised Machine Translation hasbeen advancing our ability to translatewithout parallel data, but state-of-the-artmethods assume an abundance of mono-lingual data. This paper investigates thescenario where monolingual data is lim-ited as well, finding that current unsuper-vised methods suffer in performance un-der this stricter setting. We find that theperformance loss originates from the poorquality of the pretrained monolingual em-beddings, and we propose using linguis-tic information in the embedding train-ing scheme. To support this, we look attwo linguistic features that may help im-prove alignment quality: dependency in-formation and sub-word information. Us-ing dependency-based embeddings resultsin a complementary word representationwhich offers a boost in performance ofaround 1.5 BLEU points compared to stan-dardWORD2VECwhen monolingual datais limited to 1 million sentences per lan-guage. We also find that the inclusion ofsub-word information is crucial to improv-ing the quality of the embeddings

While Neural Machine Translation (NMT) technology has been around for a few years now in research and development, it is still in its infancy when it comes to customization readiness and experience with implementation on an enterprise scale with Language Service Providers (LSPs). For large, multilanguage LSPs, it is therefore not only important to stay up-to-date on latest research on the technology as such, the best use cases, as well as main advantages and disadvantages. Moreover, due to this infancy, the challenges encountered during an early adoption of the technology in an enterprise-scale translation program are of a very practical and concrete nature and range from the quality of the NMT output over availability of language pairs in (customizable) NMT systems to additional translation workflow investments and considerations with regard to involving the supply chain. In an attempt to outline the above challenges and possible approaches to overcome them, this paper describes the migration of an established enterprise-scale machine translation program of 28 language pairs with post-editing from a Statistical Machine Translation (SMT) setup to NMT.

This paper presents a user evaluation of machine translation and post-editing for TV subtitles. Based on a process study where 12 professional subtitlers translated and post-edited subtitles, we compare effort in terms of task time and number of keystrokes. We also discuss examples of specific subtitling features like condensation, and how these features may have affected the post-editing results. In addition to overall MT quality, segmentation and timing of the subtitles are found to be important issues to be addressed in future work.

This paper updates the progress made on the PRINCIPLE project, a 2-year action funded by the European Commission un-der the Connecting Europe Facility (CEF) programme. PRINCIPLE focuses on col-lecting high-quality language resources for Croatian, Icelandic, Irish and Norwe-gian, which have been identified as low-resource languages, especially for build-ing effective machine translation (MT) systems. We report initial achievements of the project and ongoing activities aimed at promoting the uptake of neural MT for the low-resource languages of the project.