Findings of the 2016 Conference on Machine Translation

Bojar, Ondřej; Chatterjee, Rajen; Federmann, Christian; Graham, Yvette; Haddow, Barry; Huck, Matthias; Yepes, Antonio Jimeno; Koehn, Philipp; Logacheva, Varvara; Monz, Christof; Negri, Matteo; Névéol, Aurélie; Neves, Mariana; Popel, Martin; Post, Matt; Rubino, Raphaël; Scarton, Carolina; Specia, Lucia; Turchi, Marco; Verspoor, Karin; Zampieri, Marcos

doi:10.18653/v1/w16-2301

Cited by 387 publications

(354 citation statements)

References 88 publications

Supporting

Mentioning

348

Contrasting

Unclassified

Order By: Relevance

“…The second system is trained on sub-word units by using the Byte-Pair Encoding (BPE) technique (Gage, 1994), which has been proposed by Sennrich et al (2016b) as a successful way to reduce the OOV rate. The system used in our evaluation is the pre-trained model built for the best EnglishGerman submission (Sennrich et al, 2016a) at the News Translation task at WMT'16 (Bojar et al, 2016). At test stage, it is supplied with terminology lists containing term recommendations in BPE format.…”

Section: Experimental Settingmentioning

confidence: 99%

Guiding Neural Machine Translation Decoding with External Knowledge

Chatterjee¹,

Negri²,

Turchi³

et al. 2017

Proceedings of the Second Conference on Machine Translation

Self Cite

View full text Add to dashboard Cite

Differently from the phrase-based paradigm, neural machine translation (NMT) operates on word and sentence representations in a continuous space. This makes the decoding process not only more difficult to interpret, but also harder to influence with external knowledge. For the latter problem, effective solutions like the XML-markup used by phrase-based models to inject fixed translation options as constraints at decoding time are not yet available. We propose a "guide" mechanism that enhances an existing NMT decoder with the ability to prioritize and adequately handle translation options presented in the form of XML annotations of source words. Positive results obtained in two different translation tasks indicate the effectiveness of our approach.

show abstract

Section: Experimental Settingmentioning

confidence: 99%

Guiding Neural Machine Translation Decoding with External Knowledge

Chatterjee¹,

Negri²,

Turchi³

et al. 2017

Proceedings of the Second Conference on Machine Translation

Self Cite

View full text Add to dashboard Cite

show abstract

“…QuEst++ is considered to be the state-of-the-art framework for MTQE tasks and is used as a baseline in the most recent MTQE shared tasks, such as the ones in 2014 (Bojar et al, 2014), 2015 (Bojar et al, 2015), and 2016 (Bojar et al, 2016). It includes a feature extraction framework and also provides with the machine learning algorithms necessary to build the MTQE prediction models.…”

Section: The Quality Estimation Systemmentioning

confidence: 99%

Questing for Quality Estimation A User Study

Escartín

Béchara

Orăsan

2017

The Prague Bulletin of Mathematical Linguistics

View full text Add to dashboard Cite

Post-Editing of Machine Translation (MT) has become a reality in professional translation workflows. In order to optimize the management of projects that use post-editing and avoid underpayments and mistrust from professional translators, effective tools to assess the quality of Machine Translation (MT) systems need to be put in place. One field of study that could address this problem is Machine Translation Quality Estimation (MTQE), which aims to determine the quality of MT without an existing reference. Accurate and reliable MTQE can help project managers and translators alike, as it would allow estimating more precisely the cost of post-editing projects in terms of time and adequate fares by discarding those segments that are not worth post-editing (PE) and have to be translated from scratch.In this paper, we report on the results of an impact study which engages professional translators in PE tasks using MTQE. We measured translators' productivity in different scenarios: translating from scratch, post-editing without using MTQE, and post-editing using MTQE. Our results show that QE information, when accurate, improves post-editing efficiency.

show abstract

“…The latest developments of machine translation have been led by the neural approach (Sutskever et al, 2014;, a deep-learning based technique that has shown to outperform the previous methods in all the recent evaluation campaigns (Bojar et al, 2016;Cettolo et al, 2016). NMT mainly relies on parallel data, which are expensive to produce as they involve human translation.…”

Section: Introductionmentioning

confidence: 99%