Sheila Castilho

Is Neural Machine Translation the New State of the Art

Abstract This paper discusses neural machine translation (NMT), a new paradigm in the MT field, comparing the quality of NMT systems with statistical MT by describing three studies using automatic and human evaluation methods. Automatic evaluation results presented for NMT are very promising, however human evaluations show mixed results. We report increases in fluency but inconsistent results for adequacy and post-editing effort. NMT undoubtedly represents a step forward for the MT field, but one that the community should be careful not to oversell.

Human Evaluation of Multi-modal Neural Machine Translation: A Case-Study on E-Commerce Listing Titles.

In this paper, we study how humans perceive the use of images as an additional knowledge source to machine-translate usergenerated product listings in an e-commerce company. We conduct a human evaluation where we assess how a multi-modal neural machine translation (NMT) model compares to two text-only approaches: a conventional state-of-the-art attention-based NMT and a phrase-based statistical machine translation (PBSMT) model. We evaluate translations obtained with different systems and also discuss the data set of user-generated product listings, which in our case comprises both product listings and associated images. We found that humans preferred translations obtained with a PBSMT system to both text-only and multi-modal NMT over 56% of the time. Nonetheless, human evaluators ranked translations from a multi-modal NMT model as better than those of a text-only NMT over 88% of the time, which suggests that images do help NMT in this use-case.

On Education and Training in Translation Quality Assessment

In this chapter, we argue that education and training in translation quality assessment (TQA)is being neglected for most, if not all, stakeholders of the translation process, from translators, post-editors, and reviewers to buyers and end-users of translation products and services. Within academia, there is a lack of education and training opportunities to equip translation students, even at postgraduate level, with the knowledge and skills required to understand and use TQA. This has immediate effects on their employability and long-term effects on professional practice. In discussing and building upon previous initiatives to tackle this issue, we provide a range of viewpoints and resources for the provision of such opportunities in collaborative and independent contexts across all modes and academic settings, focusing not just on TQA and machine translation training, but also on the use of assessment strategies in educational contexts that are directly relevant to those used in industry. In closing, we reiterate our argument for the importance of education and training in TQA, on the basis of all the contributions and perspectives presented in the volume.

Approaches to Human and Machine Translation Quality Assessment

In both research and practice, translation quality assessment is a complex task involving a range of linguistic and extra-linguistic factors. This chapter provides a critical overview of the established and developing approaches to the definition and measurement of translation quality in human and machine translation workflows across a range of research, educational, and industry scenarios. We intertwine literature from several interrelated disciplines dealing with contemporary translation quality assessment and, while we acknowledge the need for diversity in these approaches, we argue that there are fundamental and widespread issues that remain to be addressed, if we are to consolidate our knowledge and practice of translation quality assessment in increasingly technologised environments across research, teaching, and professional practice.

Evaluating MT for massive open online courses

This article reports a multifaceted comparison between statistical and neural machine translation (MT) systems that were developed for translation of data from massive open online courses (MOOCs). The study uses four language pairs: English to German, Greek, Portuguese, and Russian. Translation quality is evaluated using automatic metrics and human evaluation, carried out by professional translators. Results show that neural MT is preferred in side-by-side ranking, and is found to contain fewer overall errors. Results are less clear-cut for some error categories, and for temporal and technical post-editing effort. In addition, results are reported based on sentence length, showing advantages and disadvantages depending on the particular language pair and MT paradigm.