The IWSLT 2016 evaluation campaign

M Cettolo, J Niehues, S Stüker… - Proceedings of the …, 2016 - aclanthology.org
Abstract The IWSLT 2016 Evaluation Campaign featured two tasks: the translation of talks
and the translation of video conference conversations. While the first task extends previously …

Stronger baselines for trustable results in neural machine translation

M Denkowski, G Neubig - arxiv preprint arxiv:1706.09733, 2017 - arxiv.org
Interest in neural machine translation has grown rapidly as its effectiveness has been
demonstrated across language and data scenarios. New research regularly introduces …

Neural versus phrase-based mt quality: An in-depth analysis on english–german and english–french

L Bentivogli, A Bisazza, M Cettolo… - Computer speech & …, 2018 - Elsevier
Within the field of statistical machine translation, the neural approach (NMT) is currently
pushing ahead the state of the art performance traditionally achieved by phrase-based …

Detecting cross-lingual semantic divergence for neural machine translation

M Carpuat, Y Vyas, X Niu - Proceedings of the First Workshop on …, 2017 - aclanthology.org
Parallel corpora are often not as parallel as one might assume: non-literal translations and
noisy translations abound, even in curated corpora routinely used for training and …

Metric score landscape challenge (MSLC23): Understanding metrics' performance on a wider landscape of translation quality

C Lo, S Larkin, R Knowles - … of the Eighth Conference on Machine …, 2023 - aclanthology.org
Abstract The Metric Score Landscape Challenge (MSLC23) dataset aims to gain insight into
metric scores on a broader/wider landscape of machine translation (MT) quality. It provides a …

Identifying semantic divergences in parallel text without annotations

Y Vyas, X Niu, M Carpuat - arxiv preprint arxiv:1803.11112, 2018 - arxiv.org
Recognizing that even correct translations are not always semantically equivalent, we
automatically detect meaning divergences in parallel sentence pairs with a deep neural …

Robust neural machine translation for clean and noisy speech transcripts

MA Di Gangi, R Enyedi, A Brusadin… - arxiv preprint arxiv …, 2019 - arxiv.org
Neural machine translation models have shown to achieve high quality when trained and
fed with well structured and punctuated input texts. Unfortunately, the latter condition is not …

[PDF][PDF] Multi-source Neural Automatic Post-Editing: FBK's participation in the WMT 2017 APE shared task

R Chatterjee, MA Farajian, M Negri… - Proceedings of the …, 2017 - aclanthology.org
Previous phrase-based approaches to Automatic Post-editing (APE) have shown that the
dependency of MT errors from the source sentence can be exploited by jointly learning from …

[PDF][PDF] Empirical investigation of optimization algorithms in neural machine translation

P Bahar, T Alkhouli… - … Prague Bulletin of …, 2017 - publications.rwth-aachen.de
Training neural networks is a non-convex and a high-dimensional optimization problem. In
this paper, we provide a comparative study of the most popular stochastic optimization …

Assessing the tolerance of neural machine translation systems against speech recognition errors

N Ruiz, MA Di Gangi, N Bertoldi, M Federico - arxiv preprint arxiv …, 2019 - arxiv.org
Machine translation systems are conventionally trained on textual resources that do not
model phenomena that occur in spoken language. While the evaluation of neural machine …