Tilde’s Machine Translation Systems for WMT 2019

Pinnis, Mārcis; Krišlauks, Rihards; Rikters, Matīss

doi:10.18653/v1/w19-5335

Cited by 4 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2.5.40 TILDE-NC-NMT and TILDE-NC-NMT (Pinnis et al, 2019) Tilde developed both constrained and unconstrained NMT systems for English-Lithuanian and Lithuanian-English using the Marian toolkit. All systems feature ensembles of four to five transformer models that were trained using the quasi-hyperbolic Adam optimiser (Ma and Yarats, 2018).…”

Section: Talp_upc_2019_kken Andmentioning

confidence: 99%

Findings of the 2019 Conference on Machine Translation (WMT19)

Barrault¹,

Bojar²,

Costa-jussà³

et al. 2019

Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

336

261

View full text Add to dashboard Cite

This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2019. Participants were asked to build machine translation systems for any of 18 language pairs, to be evaluated on a test set of news stories. The main metric for this task is human judgment of translation quality. The task was also opened up to additional test suites to probe specific aspects of translation.

show abstract

Section: Talp_upc_2019_kken Andmentioning

confidence: 99%

Findings of the 2019 Conference on Machine Translation (WMT19)

Barrault¹,

Bojar²,

Costa-jussà³

et al. 2019

Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

336

261

View full text Add to dashboard Cite

show abstract

“…• Gujarati → English (gu-en): This is one of the task's low-resource language pairs (i.e., whose test set is half the size of most languagepairs in the task), and is one where there may en-de fr-de de-cs gu-en lt-en (Pinnis et al, 2019) 0.216 77.5 NEU (Li et al, 2019) 0.213 77.0 (Barrault et al, 2019). The systems named "online-[letter]" correspond to publicly available translation services and were anonimized in the shared task.…”

Section: Datasetsmentioning

confidence: 99%

Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort

Mendonça¹,

Rei²,

Coheur³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

In Machine Translation, assessing the quality of a large amount of automatic translations can be challenging. Automatic metrics are not reliable when it comes to high performing systems. In addition, resorting to human evaluators can be expensive, especially when evaluating multiple systems. To overcome the latter challenge, we propose a novel application of online learning that, given an ensemble of Machine Translation systems, dynamically converges to the best systems, by taking advantage of the human feedback available. Our experiments on WMT'19 datasets show that our online approach quickly converges to the top-3 ranked systems for the language pairs considered, despite the lack of human feedback for many translations.

show abstract

“…lt-en GTCOM-Primary (Bei et al, 2019) 0.234 77.4 tilde-nc-nmt (Pinnis et al, 2019) 0.216 77.5 NEU (Li et al, 2019) 0.213 77.0…”

Section: Datasetsmentioning

confidence: 99%